Maintained by Difan Deng and Marius Lindauer.
The following list considers papers related to neural architecture search. It is by no means complete. If you miss a paper on the list, please let us know.
Please note that although NAS methods steadily improve, the quality of empirical evaluations in this field are still lagging behind compared to other areas in machine learning, AI and optimization. We would therefore like to share some best practices for empirical evaluations of NAS methods, which we believe will facilitate sustained and measurable progress in the field. If you are interested in a teaser, please read our blog post or directly jump to our checklist.
Transformers have gained increasing popularity in different domains. For a comprehensive list of papers focusing on Neural Architecture Search for Transformer-Based spaces, the awesome-transformer-search repo is all you need.
5555
4047.
Zhu, Huijuan; Xia, Mengzhen; Wang, Liangmin; Xu, Zhicheng; Sheng, Victor S.
A Novel Knowledge Search Structure for Android Malware Detection Journal Article
In: IEEE Transactions on Services Computing, no. 01, pp. 1-14, 5555, ISSN: 1939-1374.
@article{10750332,
title = { A Novel Knowledge Search Structure for Android Malware Detection },
author = {Huijuan Zhu and Mengzhen Xia and Liangmin Wang and Zhicheng Xu and Victor S. Sheng},
url = {https://doi.ieeecomputersociety.org/10.1109/TSC.2024.3496333},
doi = {10.1109/TSC.2024.3496333},
issn = {1939-1374},
year = {5555},
date = {5555-11-01},
urldate = {5555-11-01},
journal = {IEEE Transactions on Services Computing},
number = {01},
pages = {1-14},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
abstract = {While the Android platform is gaining explosive popularity, the number of malicious software (malware) is also increasing sharply. Thus, numerous malware detection schemes based on deep learning have been proposed. However, they are usually suffering from the cumbersome models with complex architectures and tremendous parameters. They usually require heavy computation power support, which seriously limit their deployment on actual application environments with limited resources (e.g., mobile edge devices). To surmount this challenge, we propose a novel Knowledge Distillation (KD) structure—Knowledge Search (KS). KS exploits Neural Architecture Search (NAS) to adaptively bridge the capability gap between teacher and student networks in KD by introducing a parallelized student-wise search approach. In addition, we carefully analyze the characteristics of malware and locate three cost-effective types of features closely related to malicious attacks, namely, Application Programming Interfaces (APIs), permissions and vulnerable components, to characterize Android Applications (Apps). Therefore, based on typical samples collected in recent years, we refine features while exploiting the natural relationship between them, and construct corresponding datasets. Massive experiments are conducted to investigate the effectiveness and sustainability of KS on these datasets. Our experimental results show that the proposed method yields an accuracy of 97.89% to detect Android malware, which performs better than state-of-the-art solutions.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
While the Android platform is gaining explosive popularity, the number of malicious software (malware) is also increasing sharply. Thus, numerous malware detection schemes based on deep learning have been proposed. However, they are usually suffering from the cumbersome models with complex architectures and tremendous parameters. They usually require heavy computation power support, which seriously limit their deployment on actual application environments with limited resources (e.g., mobile edge devices). To surmount this challenge, we propose a novel Knowledge Distillation (KD) structure—Knowledge Search (KS). KS exploits Neural Architecture Search (NAS) to adaptively bridge the capability gap between teacher and student networks in KD by introducing a parallelized student-wise search approach. In addition, we carefully analyze the characteristics of malware and locate three cost-effective types of features closely related to malicious attacks, namely, Application Programming Interfaces (APIs), permissions and vulnerable components, to characterize Android Applications (Apps). Therefore, based on typical samples collected in recent years, we refine features while exploiting the natural relationship between them, and construct corresponding datasets. Massive experiments are conducted to investigate the effectiveness and sustainability of KS on these datasets. Our experimental results show that the proposed method yields an accuracy of 97.89% to detect Android malware, which performs better than state-of-the-art solutions.
4046.
Zhang, Feifei; Li, Mao; Ge, Jidong; Tang, Fenghui; Zhang, Sheng; Wu, Jie; Luo, Bin
Privacy-Preserving Federated Neural Architecture Search With Enhanced Robustness for Edge Computing Journal Article
In: IEEE Transactions on Mobile Computing, no. 01, pp. 1-18, 5555, ISSN: 1558-0660.
@article{10742476,
title = { Privacy-Preserving Federated Neural Architecture Search With Enhanced Robustness for Edge Computing },
author = {Feifei Zhang and Mao Li and Jidong Ge and Fenghui Tang and Sheng Zhang and Jie Wu and Bin Luo},
url = {https://doi.ieeecomputersociety.org/10.1109/TMC.2024.3490835},
doi = {10.1109/TMC.2024.3490835},
issn = {1558-0660},
year = {5555},
date = {5555-11-01},
urldate = {5555-11-01},
journal = {IEEE Transactions on Mobile Computing},
number = {01},
pages = {1-18},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
abstract = {With the development of large-scale artificial intelligence services, edge devices are becoming essential providers of data and computing power. However, these edge devices are not immune to malicious attacks. Federated learning (FL), while protecting privacy of decentralized data through secure aggregation, struggles to trace adversaries and lacks optimization for heterogeneity. We discover that FL augmented with Differentiable Architecture Search (DARTS) can improve resilience against backdoor attacks while compatible with secure aggregation. Based on this, we propose a federated neural architecture search (NAS) framwork named SLNAS. The architecture of SLNAS is built on three pivotal components: a server-side search space generation method that employs an evolutionary algorithm with dual encodings, a federated NAS process based on DARTS, and client-side architecture tuning that utilizes Gumbel softmax combined with knowledge distillation. To validate robustness, we adapt a framework that includes backdoor attacks based on trigger optimization, data poisoning, and model poisoning, targeting both model weights and architecture parameters. Extensive experiments demonstrate that SLNAS not only effectively counters advanced backdoor attacks but also handles heterogeneity, outperforming defense baselines across a wide range of backdoor attack scenarios.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
With the development of large-scale artificial intelligence services, edge devices are becoming essential providers of data and computing power. However, these edge devices are not immune to malicious attacks. Federated learning (FL), while protecting privacy of decentralized data through secure aggregation, struggles to trace adversaries and lacks optimization for heterogeneity. We discover that FL augmented with Differentiable Architecture Search (DARTS) can improve resilience against backdoor attacks while compatible with secure aggregation. Based on this, we propose a federated neural architecture search (NAS) framwork named SLNAS. The architecture of SLNAS is built on three pivotal components: a server-side search space generation method that employs an evolutionary algorithm with dual encodings, a federated NAS process based on DARTS, and client-side architecture tuning that utilizes Gumbel softmax combined with knowledge distillation. To validate robustness, we adapt a framework that includes backdoor attacks based on trigger optimization, data poisoning, and model poisoning, targeting both model weights and architecture parameters. Extensive experiments demonstrate that SLNAS not only effectively counters advanced backdoor attacks but also handles heterogeneity, outperforming defense baselines across a wide range of backdoor attack scenarios.
4045.
Zhang, Yu-Ming; Hsieh, Jun-Wei; Lee, Chun-Chieh; Fan, Kuo-Chin
RATs-NAS: Redirection of Adjacent Trails on Graph Convolutional Networks for Predictor-based Neural Architecture Search Journal Article
In: IEEE Transactions on Artificial Intelligence, vol. 1, no. 01, pp. 1-11, 5555, ISSN: 2691-4581.
@article{10685480,
title = { RATs-NAS: Redirection of Adjacent Trails on Graph Convolutional Networks for Predictor-based Neural Architecture Search },
author = {Yu-Ming Zhang and Jun-Wei Hsieh and Chun-Chieh Lee and Kuo-Chin Fan},
url = {https://doi.ieeecomputersociety.org/10.1109/TAI.2024.3465433},
doi = {10.1109/TAI.2024.3465433},
issn = {2691-4581},
year = {5555},
date = {5555-09-01},
urldate = {5555-09-01},
journal = {IEEE Transactions on Artificial Intelligence},
volume = {1},
number = {01},
pages = {1-11},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
abstract = {Manually designed CNN architectures like VGG, ResNet, DenseNet, and MobileNet have achieved high performance across various tasks, but design them is time-consuming and costly. Neural Architecture Search (NAS) automates the discovery of effective CNN architectures, reducing the need for experts. However, evaluating candidate architectures requires significant GPU resources, leading to the use of predictor-based NAS, such as graph convolutional networks (GCN), which is the popular option to construct predictors. However, we discover that, even though the ability of GCN mimics the propagation of features of real architectures, the binary nature of the adjacency matrix limits its effectiveness. To address this, we propose Redirection of Adjacent Trails (RATs), which adaptively learns trail weights within the adjacency matrix. Our RATs-GCN outperform other predictors by dynamically adjusting trail weights after each graph convolution layer. Additionally, the proposed Divide Search Sampling (DSS) strategy, based on the observation of cell-based NAS that architectures with similar FLOPs perform similarly, enhances search efficiency. Our RATs-NAS, which combine RATs-GCN and DSS, shows significant improvements over other predictor-based NAS methods on NASBench-101, NASBench-201, and NASBench-301.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Manually designed CNN architectures like VGG, ResNet, DenseNet, and MobileNet have achieved high performance across various tasks, but design them is time-consuming and costly. Neural Architecture Search (NAS) automates the discovery of effective CNN architectures, reducing the need for experts. However, evaluating candidate architectures requires significant GPU resources, leading to the use of predictor-based NAS, such as graph convolutional networks (GCN), which is the popular option to construct predictors. However, we discover that, even though the ability of GCN mimics the propagation of features of real architectures, the binary nature of the adjacency matrix limits its effectiveness. To address this, we propose Redirection of Adjacent Trails (RATs), which adaptively learns trail weights within the adjacency matrix. Our RATs-GCN outperform other predictors by dynamically adjusting trail weights after each graph convolution layer. Additionally, the proposed Divide Search Sampling (DSS) strategy, based on the observation of cell-based NAS that architectures with similar FLOPs perform similarly, enhances search efficiency. Our RATs-NAS, which combine RATs-GCN and DSS, shows significant improvements over other predictor-based NAS methods on NASBench-101, NASBench-201, and NASBench-301.
4044.
Chen, X.; Yang, C.
CIMNet: Joint Search for Neural Network and Computing-in-Memory Architecture Journal Article
In: IEEE Micro, no. 01, pp. 1-12, 5555, ISSN: 1937-4143.
@article{10551739,
title = {CIMNet: Joint Search for Neural Network and Computing-in-Memory Architecture},
author = {X. Chen and C. Yang},
url = {https://www.computer.org/csdl/magazine/mi/5555/01/10551739/1XyKBmSlmPm},
doi = {10.1109/MM.2024.3409068},
issn = {1937-4143},
year = {5555},
date = {5555-06-01},
urldate = {5555-06-01},
journal = {IEEE Micro},
number = {01},
pages = {1-12},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
abstract = {Computing-in-memory (CIM) architecture has been proven to effectively transcend the memory wall bottleneck, expanding the potential of low-power and high-throughput applications such as machine learning. Neural architecture search (NAS) designs ML models to meet a variety of accuracy, latency, and energy constraints. However, integrating CIM into NAS presents a major challenge due to additional simulation overhead from the non-ideal characteristics of CIM hardware. This work introduces a quantization and device aware accuracy predictor that jointly scores quantization policy, CIM architecture, and neural network architecture, eliminating the need for time-consuming simulations in the search process. We also propose reducing the search space based on architectural observations, resulting in a well-pruned search space customized for CIM. These allow for efficient exploration of superior combinations in mere CPU minutes. Our methodology yields CIMNet, which consistently improves the trade-off between accuracy and hardware efficiency on benchmarks, providing valuable architectural insights.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Computing-in-memory (CIM) architecture has been proven to effectively transcend the memory wall bottleneck, expanding the potential of low-power and high-throughput applications such as machine learning. Neural architecture search (NAS) designs ML models to meet a variety of accuracy, latency, and energy constraints. However, integrating CIM into NAS presents a major challenge due to additional simulation overhead from the non-ideal characteristics of CIM hardware. This work introduces a quantization and device aware accuracy predictor that jointly scores quantization policy, CIM architecture, and neural network architecture, eliminating the need for time-consuming simulations in the search process. We also propose reducing the search space based on architectural observations, resulting in a well-pruned search space customized for CIM. These allow for efficient exploration of superior combinations in mere CPU minutes. Our methodology yields CIMNet, which consistently improves the trade-off between accuracy and hardware efficiency on benchmarks, providing valuable architectural insights.
4043.
Siddique, Ayesha; Hoque, Khaza Anuarul
Explainable AI-Guided Neural Architecture Search for Adversarial Robustness in Approximate DNNs Journal Article
In: IEEE Transactions on Sustainable Computing, no. 01, pp. 1-15, 5555, ISSN: 2377-3782.
@article{10966055,
title = { Explainable AI-Guided Neural Architecture Search for Adversarial Robustness in Approximate DNNs },
author = {Ayesha Siddique and Khaza Anuarul Hoque},
url = {https://doi.ieeecomputersociety.org/10.1109/TSUSC.2025.3561603},
doi = {10.1109/TSUSC.2025.3561603},
issn = {2377-3782},
year = {5555},
date = {5555-04-01},
urldate = {5555-04-01},
journal = {IEEE Transactions on Sustainable Computing},
number = {01},
pages = {1-15},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
abstract = {Deep neural networks are lucrative targets of adversarial attacks and approximate deep neural networks (AxDNNs) are no exception. Searching manually for adversarially robust AxDNN architectures incurs outrageous time and human effort. In this paper, we propose XAI-NAS, an explainable neural architecture search (NAS) method that leverages explainable artificial intelligence (XAI) to efficiently co-optimize the adversarial robustness and hardware efficiency of AxDNN architectures on systolic-array hardware accelerators. During the NAS process, AxDNN architectures are evolved layer-wise with heterogeneous approximate multipliers to deliver the best trade-offs between adversarial robustness, energy consumption, latency, and memory footprint. The most suitable approximate multipliers are automatically selected from an open-source Evoapprox8b library. Our extensive evaluations provide a set of Pareto optimal hardware efficient and adversarially robust solutions. For example, a Pareto-optimal DNN AxDNN for the MNIST and CIFAR-10 datasets exhibits up to 1.5× higher adversarial robustness, 2.1× less energy consumption, 4.39× reduced latency, and 2.37× low memory footprint when compared to the state-of-the-art NAS approaches.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Deep neural networks are lucrative targets of adversarial attacks and approximate deep neural networks (AxDNNs) are no exception. Searching manually for adversarially robust AxDNN architectures incurs outrageous time and human effort. In this paper, we propose XAI-NAS, an explainable neural architecture search (NAS) method that leverages explainable artificial intelligence (XAI) to efficiently co-optimize the adversarial robustness and hardware efficiency of AxDNN architectures on systolic-array hardware accelerators. During the NAS process, AxDNN architectures are evolved layer-wise with heterogeneous approximate multipliers to deliver the best trade-offs between adversarial robustness, energy consumption, latency, and memory footprint. The most suitable approximate multipliers are automatically selected from an open-source Evoapprox8b library. Our extensive evaluations provide a set of Pareto optimal hardware efficient and adversarially robust solutions. For example, a Pareto-optimal DNN AxDNN for the MNIST and CIFAR-10 datasets exhibits up to 1.5× higher adversarial robustness, 2.1× less energy consumption, 4.39× reduced latency, and 2.37× low memory footprint when compared to the state-of-the-art NAS approaches.
4042.
Dong, Yukang; Pan, Fanxing; Gui, Yi; Jiang, Wenbin; Wan, Yao; Zheng, Ran; Jin, Hai
Comprehensive Architecture Search for Deep Graph Neural Networks Journal Article
In: IEEE Transactions on Big Data, no. 01, pp. 1-15, 5555, ISSN: 2332-7790.
@article{10930718,
title = { Comprehensive Architecture Search for Deep Graph Neural Networks },
author = {Yukang Dong and Fanxing Pan and Yi Gui and Wenbin Jiang and Yao Wan and Ran Zheng and Hai Jin},
url = {https://doi.ieeecomputersociety.org/10.1109/TBDATA.2025.3552336},
doi = {10.1109/TBDATA.2025.3552336},
issn = {2332-7790},
year = {5555},
date = {5555-03-01},
urldate = {5555-03-01},
journal = {IEEE Transactions on Big Data},
number = {01},
pages = {1-15},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
abstract = {In recent years, Neural Architecture Search (NAS) has emerged as a promising approach for automatically discovering superior model architectures for deep Graph Neural Networks (GNNs). Different methods have paid attention to different types of search spaces. However, due to the time-consuming nature of training deep GNNs, existing NAS methods often fail to explore diverse search spaces sufficiently, which constrains their effectiveness. To crack this hard nut, we propose CAS-DGNN, a novel comprehensive architecture search method for deep GNNs. It encompasses four kinds of search spaces that are the composition of aggregate and update operators, different types of aggregate operators, residual connections, and hyper-parameters. To meet the needs of such a complex situation, a phased and hybrid search strategy is proposed to accommodate the diverse characteristics of different search spaces. Specifically, we divide the search process into four phases, utilizing evolutionary algorithms and Bayesian optimization. Meanwhile, we design two distinct search methods for residual connections (All-connected search and Initial Residual search) to streamline the search space, which enhances the scalability of CAS-DGNN. The experimental results show that CAS-DGNN achieves higher accuracy with competitive search costs across ten public datasets compared to existing methods.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
In recent years, Neural Architecture Search (NAS) has emerged as a promising approach for automatically discovering superior model architectures for deep Graph Neural Networks (GNNs). Different methods have paid attention to different types of search spaces. However, due to the time-consuming nature of training deep GNNs, existing NAS methods often fail to explore diverse search spaces sufficiently, which constrains their effectiveness. To crack this hard nut, we propose CAS-DGNN, a novel comprehensive architecture search method for deep GNNs. It encompasses four kinds of search spaces that are the composition of aggregate and update operators, different types of aggregate operators, residual connections, and hyper-parameters. To meet the needs of such a complex situation, a phased and hybrid search strategy is proposed to accommodate the diverse characteristics of different search spaces. Specifically, we divide the search process into four phases, utilizing evolutionary algorithms and Bayesian optimization. Meanwhile, we design two distinct search methods for residual connections (All-connected search and Initial Residual search) to streamline the search space, which enhances the scalability of CAS-DGNN. The experimental results show that CAS-DGNN achieves higher accuracy with competitive search costs across ten public datasets compared to existing methods.
4041.
Yan, J.; Liu, J.; Xu, H.; Wang, Z.; Qiao, C.
Peaches: Personalized Federated Learning with Neural Architecture Search in Edge Computing Journal Article
In: IEEE Transactions on Mobile Computing, no. 01, pp. 1-17, 5555, ISSN: 1558-0660.
@article{10460163,
title = {Peaches: Personalized Federated Learning with Neural Architecture Search in Edge Computing},
author = {J. Yan and J. Liu and H. Xu and Z. Wang and C. Qiao},
doi = {10.1109/TMC.2024.3373506},
issn = {1558-0660},
year = {5555},
date = {5555-03-01},
urldate = {5555-03-01},
journal = {IEEE Transactions on Mobile Computing},
number = {01},
pages = {1-17},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
abstract = {In edge computing (EC), federated learning (FL) enables numerous distributed devices (or workers) to collaboratively train AI models without exposing their local data. Most works of FL adopt a predefined architecture on all participating workers for model training. However, since workers' local data distributions vary heavily in EC, the predefined architecture may not be the optimal choice for every worker. It is also unrealistic to manually design a high-performance architecture for each worker, which requires intense human expertise and effort. In order to tackle this challenge, neural architecture search (NAS) has been applied in FL to automate the architecture design process. Unfortunately, the existing federated NAS frameworks often suffer from the difficulties of system heterogeneity and resource limitation. To remedy this problem, we present a novel framework, termed Peaches, to achieve efficient searching and training in the resource-constrained EC system. Specifically, the local model of each worker is stacked by base cell and personal cell, where the base cell is shared by all workers to capture the common knowledge and the personal cell is customized for each worker to fit the local data. We determine the number of base cells, shared by all workers, according to the bandwidth budget on the parameters server. Besides, to relieve the data and system heterogeneity, we find the optimal number of personal cells for each worker based on its computing capability. In addition, we gradually prune the search space during training to mitigate the resource consumption. We evaluate the performance of Peaches through extensive experiments, and the results show that Peaches can achieve an average accuracy improvement of about 6.29% and up to 3.97× speed up compared with the baselines.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
In edge computing (EC), federated learning (FL) enables numerous distributed devices (or workers) to collaboratively train AI models without exposing their local data. Most works of FL adopt a predefined architecture on all participating workers for model training. However, since workers' local data distributions vary heavily in EC, the predefined architecture may not be the optimal choice for every worker. It is also unrealistic to manually design a high-performance architecture for each worker, which requires intense human expertise and effort. In order to tackle this challenge, neural architecture search (NAS) has been applied in FL to automate the architecture design process. Unfortunately, the existing federated NAS frameworks often suffer from the difficulties of system heterogeneity and resource limitation. To remedy this problem, we present a novel framework, termed Peaches, to achieve efficient searching and training in the resource-constrained EC system. Specifically, the local model of each worker is stacked by base cell and personal cell, where the base cell is shared by all workers to capture the common knowledge and the personal cell is customized for each worker to fit the local data. We determine the number of base cells, shared by all workers, according to the bandwidth budget on the parameters server. Besides, to relieve the data and system heterogeneity, we find the optimal number of personal cells for each worker based on its computing capability. In addition, we gradually prune the search space during training to mitigate the resource consumption. We evaluate the performance of Peaches through extensive experiments, and the results show that Peaches can achieve an average accuracy improvement of about 6.29% and up to 3.97× speed up compared with the baselines.
4040.
Sun, Genchen; Liu, Zhengkun; Gan, Lin; Su, Hang; Li, Ting; Zhao, Wenfeng; Sun, Biao
SpikeNAS-Bench: Benchmarking NAS Algorithms for Spiking Neural Network Architecture Journal Article
In: IEEE Transactions on Artificial Intelligence, vol. 1, no. 01, pp. 1-12, 5555, ISSN: 2691-4581.
@article{10855683,
title = { SpikeNAS-Bench: Benchmarking NAS Algorithms for Spiking Neural Network Architecture },
author = {Genchen Sun and Zhengkun Liu and Lin Gan and Hang Su and Ting Li and Wenfeng Zhao and Biao Sun},
url = {https://doi.ieeecomputersociety.org/10.1109/TAI.2025.3534136},
doi = {10.1109/TAI.2025.3534136},
issn = {2691-4581},
year = {5555},
date = {5555-01-01},
urldate = {5555-01-01},
journal = {IEEE Transactions on Artificial Intelligence},
volume = {1},
number = {01},
pages = {1-12},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
abstract = {In recent years, Neural Architecture Search (NAS) has marked significant advancements, yet its efficacy is marred by the dependence on substantial computational resources. To mitigate this, the development of NAS benchmarks has emerged, offering datasets that enumerate all potential network architectures and their performances within a predefined search space. Nonetheless, these benchmarks predominantly focus on convolutional architectures, which are criticized for their limited interpretability and suboptimal hardware efficiency. Recognizing the untapped potential of Spiking Neural Networks (SNNs) — often hailed as the third generation of neural networks for their biological realism and computational thrift — this study introduces SpikeNAS-Bench. As a pioneering benchmark for SNN, SpikeNAS-Bench utilizes a cell-based search space, integrating leaky integrate-and-fire (LIF) neurons with variable thresholds as candidate operations. It encompasses 15,625 candidate architectures, rigorously evaluated on CIFAR10, CIFAR100 and Tiny-ImageNet datasets. This paper delves into the architectural nuances of SpikeNAS-Bench, leveraging various criteria to underscore the benchmark’s utility and presenting insights that could steer future NAS algorithm designs. Moreover, we assess the benchmark’s consistency through three distinct proxy types: zero-cost-based, early-stop-based, and predictor-based proxies. Additionally, the paper benchmarks seven contemporary NAS algorithms to attest to SpikeNAS-Bench’s broad applicability. We commit to providing training logs, diagnostic data for all candidate architectures, and the promise to release all code and datasets post-acceptance, aiming to catalyze further exploration and innovation within the SNN domain. SpikeNAS-Bench is open source at https://github.com/XXX (hidden for double anonymous review).},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
In recent years, Neural Architecture Search (NAS) has marked significant advancements, yet its efficacy is marred by the dependence on substantial computational resources. To mitigate this, the development of NAS benchmarks has emerged, offering datasets that enumerate all potential network architectures and their performances within a predefined search space. Nonetheless, these benchmarks predominantly focus on convolutional architectures, which are criticized for their limited interpretability and suboptimal hardware efficiency. Recognizing the untapped potential of Spiking Neural Networks (SNNs) — often hailed as the third generation of neural networks for their biological realism and computational thrift — this study introduces SpikeNAS-Bench. As a pioneering benchmark for SNN, SpikeNAS-Bench utilizes a cell-based search space, integrating leaky integrate-and-fire (LIF) neurons with variable thresholds as candidate operations. It encompasses 15,625 candidate architectures, rigorously evaluated on CIFAR10, CIFAR100 and Tiny-ImageNet datasets. This paper delves into the architectural nuances of SpikeNAS-Bench, leveraging various criteria to underscore the benchmark’s utility and presenting insights that could steer future NAS algorithm designs. Moreover, we assess the benchmark’s consistency through three distinct proxy types: zero-cost-based, early-stop-based, and predictor-based proxies. Additionally, the paper benchmarks seven contemporary NAS algorithms to attest to SpikeNAS-Bench’s broad applicability. We commit to providing training logs, diagnostic data for all candidate architectures, and the promise to release all code and datasets post-acceptance, aiming to catalyze further exploration and innovation within the SNN domain. SpikeNAS-Bench is open source at https://github.com/XXX (hidden for double anonymous review).
4039.
Li, Changlin; Lin, Sihao; Tang, Tao; Wang, Guangrun; Li, Mingjie; Li, Zhihui; Chang, Xiaojun
BossNAS Family: Block-wisely Self-supervised Neural Architecture Search Journal Article
In: IEEE Transactions on Pattern Analysis & Machine Intelligence, no. 01, pp. 1-15, 5555, ISSN: 1939-3539.
@article{10839629,
title = { BossNAS Family: Block-wisely Self-supervised Neural Architecture Search },
author = {Changlin Li and Sihao Lin and Tao Tang and Guangrun Wang and Mingjie Li and Zhihui Li and Xiaojun Chang},
url = {https://doi.ieeecomputersociety.org/10.1109/TPAMI.2025.3529517},
doi = {10.1109/TPAMI.2025.3529517},
issn = {1939-3539},
year = {5555},
date = {5555-01-01},
urldate = {5555-01-01},
journal = {IEEE Transactions on Pattern Analysis & Machine Intelligence},
number = {01},
pages = {1-15},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
abstract = {Recent advances in hand-crafted neural architectures for visual recognition underscore the pressing need to explore architecture designs comprising diverse building blocks. Concurrently, neural architecture search (NAS) methods have gained traction as a means to alleviate human efforts. Nevertheless, the question of whether NAS methods can efficiently and effectively manage diversified search spaces featuring disparate candidates, such as Convolutional Neural Networks (CNNs) and transformers, remains an open question. In this work, we introduce a novel unsupervised NAS approach called BossNAS (Block-wisely Self-supervised Neural Architecture Search), which aims to address the problem of inaccurate predictive architecture ranking caused by a large weight-sharing space while mitigating potential ranking issue caused by biased supervision. To achieve this, we factorize the search space into blocks and introduce a novel self-supervised training scheme called Ensemble Bootstrapping, to train each block separately in an unsupervised manner. In the search phase, we propose an unsupervised Population-Centric Search, optimizing the candidate architecture towards the population center. Additionally, we enhance our NAS method by integrating masked image modeling and present BossNAS++ to overcome the lack of dense supervision in our block-wise self-supervised NAS. In BossNAS++, we introduce the training technique named Masked Ensemble Bootstrapping for block-wise supernet, accompanied by a Masked Population-Centric Search scheme to promote fairer architecture selection. Our family of models, discovered through BossNAS and BossNAS++, delivers impressive results across various search spaces and datasets. Our transformer model discovered by BossNAS++ attains a remarkable accuracy of 83.2% on ImageNet with only 10.5B MAdds, surpassing DeiT-B by 1.4% while maintaining a lower computation cost. Moreover, our approach excels in architecture rating accuracy, achieving Spearman correlations of 0.78 and 0.76 on the canonical MBConv search space with ImageNet and the NATS-Bench size search space with CIFAR-100, respectively, outperforming state-of-the-art NAS methods.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Recent advances in hand-crafted neural architectures for visual recognition underscore the pressing need to explore architecture designs comprising diverse building blocks. Concurrently, neural architecture search (NAS) methods have gained traction as a means to alleviate human efforts. Nevertheless, the question of whether NAS methods can efficiently and effectively manage diversified search spaces featuring disparate candidates, such as Convolutional Neural Networks (CNNs) and transformers, remains an open question. In this work, we introduce a novel unsupervised NAS approach called BossNAS (Block-wisely Self-supervised Neural Architecture Search), which aims to address the problem of inaccurate predictive architecture ranking caused by a large weight-sharing space while mitigating potential ranking issue caused by biased supervision. To achieve this, we factorize the search space into blocks and introduce a novel self-supervised training scheme called Ensemble Bootstrapping, to train each block separately in an unsupervised manner. In the search phase, we propose an unsupervised Population-Centric Search, optimizing the candidate architecture towards the population center. Additionally, we enhance our NAS method by integrating masked image modeling and present BossNAS++ to overcome the lack of dense supervision in our block-wise self-supervised NAS. In BossNAS++, we introduce the training technique named Masked Ensemble Bootstrapping for block-wise supernet, accompanied by a Masked Population-Centric Search scheme to promote fairer architecture selection. Our family of models, discovered through BossNAS and BossNAS++, delivers impressive results across various search spaces and datasets. Our transformer model discovered by BossNAS++ attains a remarkable accuracy of 83.2% on ImageNet with only 10.5B MAdds, surpassing DeiT-B by 1.4% while maintaining a lower computation cost. Moreover, our approach excels in architecture rating accuracy, achieving Spearman correlations of 0.78 and 0.76 on the canonical MBConv search space with ImageNet and the NATS-Bench size search space with CIFAR-100, respectively, outperforming state-of-the-art NAS methods.
2025
4038.
Wang, Weiqi; Bao, Feilong; Xing, Zhecong; Lian, Zhe
A Survey: Research Progress of Feature Fusion Technology Journal Article
In: 2025.
@article{wangsurvey,
title = {A Survey: Research Progress of Feature Fusion Technology},
author = {Weiqi Wang and Feilong Bao and Zhecong Xing and Zhe Lian},
url = {http://poster-openaccess.com/files/ICIC2024/862.pdf},
year = {2025},
date = {2025-12-01},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
4037.
(Ed.)
MACHINE-GENERATED NEURAL NETWORKS FOR SHORT-TERM LOAD FORECASTING Collection
2025.
@collection{nokey,
title = { MACHINE-GENERATED NEURAL NETWORKS FOR SHORT-TERM LOAD FORECASTING},
author = {Gergana Vacheva and Plamen Stanchev and Nikolay Hinov
},
url = {https://unitechsp.tugab.bg/images/2024/1-EE/s1_p143_v1.pdf},
year = {2025},
date = {2025-12-01},
urldate = {2025-12-01},
booktitle = {International Scientific Conference UNITECH`2024},
journal = {International Scientific Conference UNITECH`2024},
keywords = {},
pubstate = {published},
tppubtype = {collection}
}
4036.
Lan, Guojun; Tang, Jian; Chen, Jie; Xing, Jingshu; Zhao, Lijun
An effective dual-predictor controller mechanism using neural architecture search for optimization of residential energy hub system Journal Article
In: Discover Computing , vol. 28, 2025.
@article{nokey,
title = {An effective dual-predictor controller mechanism using neural architecture search for optimization of residential energy hub system},
author = {Guojun Lan and Jian Tang and Jie Chen and Jingshu Xing and Lijun Zhao
},
url = {https://link.springer.com/article/10.1007/s10791-025-09533-1},
year = {2025},
date = {2025-04-09},
urldate = {2025-04-09},
journal = {Discover Computing },
volume = {28},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
4035.
Wu, Yue; Huang, Lin; Yang, Tiejun
Breast Ultrasound Image Segmentation Using Multi-branch Skip Connection Search Journal Article
In: Journal of Imaging Informatics in Medicine , 2025.
@article{wu-jiim25a,
title = {Breast Ultrasound Image Segmentation Using Multi-branch Skip Connection Search},
author = { Yue Wu and Lin Huang and Tiejun Yang
},
url = {https://link.springer.com/article/10.1007/s10278-025-01487-6},
year = {2025},
date = {2025-04-01},
urldate = {2025-04-01},
journal = {Journal of Imaging Informatics in Medicine },
keywords = {},
pubstate = {published},
tppubtype = {article}
}
4034.
CAPELLO, ALESSIO
An End-to-End Edge-Computing Framework for IoT-enabled Monitoring PhD Thesis
2025.
@phdthesis{nokey,
title = {An End-to-End Edge-Computing Framework for IoT-enabled Monitoring},
author = { CAPELLO, ALESSIO },
url = {https://tesidottorato.depositolegale.it/handle/20.500.14242/199679?mode=simple},
year = {2025},
date = {2025-04-01},
urldate = {2025-04-01},
keywords = {},
pubstate = {published},
tppubtype = {phdthesis}
}
4033.
Toe, Seb Gregory Dal; Tiddeman, Bernard; Zarges, Christine
Evolutionary Neural Architecture Search using Random Weight Distributions Proceedings Article
In: Ochoa, Gabriela (Ed.): Proceedings of the Genetic and Evolutionary Computation Conference Companion, GECCO 2025, Málaga, Spain, July 14-18, 2025, Association for Computing Machinery (ACM), United States of America, 2025, (GECCO 2025 : The Genetic and Evolutionary Computation Conference, GECCO ; Conference date: 14-07-2025 Through 18-07-2025).
@inproceedings{581d1ec7c5934c3db7cf4e0f5c2b67f1,
title = {Evolutionary Neural Architecture Search using Random Weight Distributions},
author = {Seb Gregory Dal Toe and Bernard Tiddeman and Christine Zarges},
editor = {Gabriela Ochoa},
url = {https://gecco-2025.sigevo.org/HomePage},
doi = {10.1145/3712255.3726664},
year = {2025},
date = {2025-03-19},
urldate = {2025-03-19},
booktitle = {Proceedings of the Genetic and Evolutionary Computation Conference Companion, GECCO 2025, Málaga, Spain, July 14-18, 2025},
publisher = {Association for Computing Machinery (ACM)},
address = {United States of America},
abstract = {We consider the problem of efficiently searching for high-performing neural architectures whilst simultaneously favouring networks of reduced complexity. It is theorised that a complementary set of proxies can be employed for multi-objective optimisation to balance model performance with the size of the network. We demonstrate that a low-cost proxy for the test accuracy of a candidate architecture can be derived from a series of inferences alone. The proxy is paired with a complexity metric based on the number of parameters in the model and the two properties are used in a multi-objective setting. A Pareto Archived Evolutionary Strategy is used to optimise the two objectives simultaneously and deliver a diverse collection of solutions as output. This method is shown to successfully discover low-complexity architectures with minor loss of accuracy as compared to the global optima and does so with statistical reliability. This work offers a proof-of-concept Neural Architecture Search algorithm that removes training from the process entirely. The proposed approach is examined in terms of search behaviour and the complexity reduction that can be achieved by comparing discovered solutions to the top-performing architectures in the search space.},
note = {GECCO 2025 : The Genetic and Evolutionary Computation Conference, GECCO ; Conference date: 14-07-2025 Through 18-07-2025},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We consider the problem of efficiently searching for high-performing neural architectures whilst simultaneously favouring networks of reduced complexity. It is theorised that a complementary set of proxies can be employed for multi-objective optimisation to balance model performance with the size of the network. We demonstrate that a low-cost proxy for the test accuracy of a candidate architecture can be derived from a series of inferences alone. The proxy is paired with a complexity metric based on the number of parameters in the model and the two properties are used in a multi-objective setting. A Pareto Archived Evolutionary Strategy is used to optimise the two objectives simultaneously and deliver a diverse collection of solutions as output. This method is shown to successfully discover low-complexity architectures with minor loss of accuracy as compared to the global optima and does so with statistical reliability. This work offers a proof-of-concept Neural Architecture Search algorithm that removes training from the process entirely. The proposed approach is examined in terms of search behaviour and the complexity reduction that can be achieved by comparing discovered solutions to the top-performing architectures in the search space.
4032.
Tran, Thanh Hai; Nguyen, Dac Tam; Ngo, Minh Duc; Doan, Long; Luong, Ngoc Hoang; Binh, Huynh Thi Thanh
Kernelshap-nas: a shapley additive explanatory approach for characterizing operation influences Journal Article
In: Neural Computing and Applications , 2025.
@article{nokey,
title = {Kernelshap-nas: a shapley additive explanatory approach for characterizing operation influences},
author = {Thanh Hai Tran and Dac Tam Nguyen and Minh Duc Ngo and Long Doan and Ngoc Hoang Luong and Huynh Thi Thanh Binh
},
url = {https://link.springer.com/article/10.1007/s00521-025-11071-2},
year = {2025},
date = {2025-03-05},
urldate = {2025-03-05},
journal = {Neural Computing and Applications },
keywords = {},
pubstate = {published},
tppubtype = {article}
}
4031.
Ju, Moran; Niu, Buniu; Li, Mulin; Mao, Tengkai; Jin, Si-nian
Toward Better Accuracy-Efficiency Trade-Offs for Oriented SAR Ship Object Detection Bachelor Thesis
2025.
@bachelorthesis{ju-jstaeors,
title = {Toward Better Accuracy-Efficiency Trade-Offs for Oriented SAR Ship Object Detection},
author = {Moran Ju and Buniu Niu and Mulin Li and Tengkai Mao and Si-nian Jin},
url = {https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=10944503},
year = {2025},
date = {2025-03-01},
urldate = {2025-03-01},
journal = { IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. },
keywords = {},
pubstate = {published},
tppubtype = {bachelorthesis}
}
4030.
Liu, Guoqing; Qian, Yuhua; Liang, Xinyan; Fu, Pinhan
Core structure-guided multi-modal classification via Monte Carlo Tree Search Journal Article
In: International Journal of Machine Learning and Cybernetics , 2025.
@article{liu-ijmlc25a,
title = {Core structure-guided multi-modal classification via Monte Carlo Tree Search},
author = { Guoqing Liu and Yuhua Qian and Xinyan Liang and Pinhan Fu
},
url = {https://link.springer.com/article/10.1007/s13042-025-02606-z},
year = {2025},
date = {2025-03-01},
urldate = {2025-03-01},
journal = {International Journal of Machine Learning and Cybernetics },
keywords = {},
pubstate = {published},
tppubtype = {article}
}
4029.
HERNANDEZ, ESAU ALAIN HERVERT; CAO, YAN; KEHTARNAVAZ, NASSER
Computationally Efficient Neural Architecture Search for Image Denoising Bachelor Thesis
2025.
@bachelorthesis{nokey,
title = {Computationally Efficient Neural Architecture Search for Image Denoising},
author = {ESAU ALAIN HERVERT HERNANDEZ and YAN CAO and NASSER KEHTARNAVAZ},
url = {https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=10948435},
year = {2025},
date = {2025-03-01},
urldate = {2025-03-01},
journal = {IEEE Access},
keywords = {},
pubstate = {published},
tppubtype = {bachelorthesis}
}
4028.
Naayini, Prudhvi; Kamatala, Srikanth; Myakala, Praveen Kumar
Transforming Performance Engineering with Generative AI Journal Article
In: Journal of Computer and Communications , vol. 13, no. 3, 2025.
@article{Naayini-jcc25a,
title = { Transforming Performance Engineering with Generative AI },
author = { Prudhvi Naayini and Srikanth Kamatala and Praveen Kumar Myakala},
url = {https://www.scirp.org/journal/paperinformation?paperid=141454},
year = {2025},
date = {2025-03-01},
urldate = {2025-03-01},
journal = {Journal of Computer and Communications },
volume = {13},
number = {3},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
4027.
Xu, Dikai; Cao, Bin
Adaptive Multiobjective Evolutionary Generative Adversarial Network for Metaverse Network Intrusion Detection Journal Article
In: Science Partner Journals, 2025.
@article{nokey,
title = {Adaptive Multiobjective Evolutionary Generative Adversarial Network for Metaverse Network Intrusion Detection},
author = {Dikai Xu and Bin Cao},
url = {https://spj.science.org/doi/pdf/10.34133/research.0665},
year = {2025},
date = {2025-03-01},
urldate = {2025-03-01},
journal = {Science Partner Journals},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
4026.
Li, Yuangang; Ma, Rui; Zhang, Qian; Wang, Zeyu; Zong, Linlin; Liu, Xinyue
Neural architecture search using attention enhanced precise path evaluation and efficient forward evolution Journal Article
In: scientific reports , 2025.
@article{nokey,
title = {Neural architecture search using attention enhanced precise path evaluation and efficient forward evolution},
author = {Yuangang Li and Rui Ma and Qian Zhang and Zeyu Wang and Linlin Zong and Xinyue Liu
},
url = {https://www.nature.com/articles/s41598-025-94187-8},
year = {2025},
date = {2025-03-01},
urldate = {2025-03-01},
booktitle = {scientific reports },
journal = {scientific reports },
keywords = {},
pubstate = {published},
tppubtype = {article}
}
4025.
(Ed.)
HPE-DARTS: Hybrid Pruning and Proxy Evaluation in Differentiable Architecture Search Collection
2025.
@collection{lin-,
title = {HPE-DARTS: Hybrid Pruning and Proxy Evaluation in Differentiable Architecture Search},
author = {Hung-I Lin and Lin-Jing Kuo and Sheng-De Wang},
url = {https://www.scitepress.org/Papers/2025/131487/131487.pdf},
year = {2025},
date = {2025-03-01},
urldate = {2025-03-01},
booktitle = {Proceedings of the 17th International Conference on Agents and Artificial Intelligence (ICAART 2025)},
journal = {Proceedings of the 17th International Conference on Agents and Artificial Intelligence (ICAART 2025)},
keywords = {},
pubstate = {published},
tppubtype = {collection}
}
4024.
(Ed.)
2025.
@collection{Friderikos-dte25a,
title = {OPTIMIZED LSTM NEURAL NETWORKS VIA NEURAL ARCHITECTURE SEARCH FOR PREDICTING DAMAGE EVOLUTION IN COMPOSITE LAMINATES},
author = {O. Friderikos and A. Mendoza and Emmanuel Baranger and D. Sagris and C. David},
url = {https://congressarchive.cimne.com/dte_aicomas_2025/abstracts/b8d1d10a96b711efba01000c29ddfc0c.pdf},
year = {2025},
date = {2025-03-01},
urldate = {2025-03-01},
booktitle = {Digital Twins in Engineering & Artificial Intelligence and Computational Methods in Applied Science, DTE - AICOMAS 2025},
keywords = {},
pubstate = {published},
tppubtype = {collection}
}
4023.
Fang, Xuwei; Xie, Weisheng; Li, Hui; Zhou, Wenbin; Hang, Chen; Gao, Xiangxiang
DARTS-EAST: an edge-adaptive selection with topology first differentiable architecture selection method Journal Article
In: Applied Intelligence , 2025.
@article{fang-ai25a,
title = {DARTS-EAST: an edge-adaptive selection with topology first differentiable architecture selection method},
author = {Xuwei Fang and Weisheng Xie and Hui Li and Wenbin Zhou and Chen Hang and Xiangxiang Gao
},
url = {https://link.springer.com/article/10.1007/s10489-025-06353-0},
year = {2025},
date = {2025-03-01},
urldate = {2025-03-01},
journal = {Applied Intelligence },
keywords = {},
pubstate = {published},
tppubtype = {article}
}
4022.
(Ed.)
Neural Architecture Search: Tradeoff Between Performance and Efficiency Collection
2025.
@collection{nokey,
title = {Neural Architecture Search: Tradeoff Between Performance and Efficiency},
author = {Tien Dung Nguyen and Nassim Mokhtari and Alexis Nédélec},
url = {https://www.scitepress.org/Papers/2025/132969/132969.pdf},
year = {2025},
date = {2025-03-01},
urldate = {2025-03-01},
booktitle = {Proceedings of the 17th International Conference on Agents and Artificial Intelligence (ICAART 2025)},
keywords = {},
pubstate = {published},
tppubtype = {collection}
}
4021.
(Ed.)
PQNAS: Mixed-precision Quantization-aware Neural Architecture Search with Pseudo Quantizer Collection
2025.
@collection{gao-icassp25a,
title = {PQNAS: Mixed-precision Quantization-aware Neural Architecture Search with Pseudo Quantizer},
author = {Tianxiao Gao and Li Guo and Shihao Wang and Shiai Zhu and Dajiang Zhou},
url = {https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=10888233},
year = {2025},
date = {2025-03-01},
urldate = {2025-03-01},
booktitle = {2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
keywords = {},
pubstate = {published},
tppubtype = {collection}
}
4020.
He, Zhimin; Chen, Hongxiang; Zhou, Yan; Situ, Haozhen; Li, Yongyao; Li, Lvzhou
Self-supervised representation learning for Bayesian quantum architecture search Journal Article
In: Phys. Rev. A, vol. 111, iss. 3, pp. 032403, 2025.
@article{PhysRevA.111.032403,
title = {Self-supervised representation learning for Bayesian quantum architecture search},
author = {Zhimin He and Hongxiang Chen and Yan Zhou and Haozhen Situ and Yongyao Li and Lvzhou Li},
url = {https://link.aps.org/doi/10.1103/PhysRevA.111.032403},
doi = {10.1103/PhysRevA.111.032403},
year = {2025},
date = {2025-03-01},
urldate = {2025-03-01},
journal = {Phys. Rev. A},
volume = {111},
issue = {3},
pages = {032403},
publisher = {American Physical Society},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
4019.
Feng, Shiyang; Li, Zhaowei; Zhang, Bo; Chen, Tao
DSF2-NAS: Dual-Stage Feature Fusion via Network Architecture Search for Classification of Multimodal Remote Sensing Images Journal Article
In: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. , 2025.
@article{feng-ieeejstoaeors25a,
title = {DSF2-NAS: Dual-Stage Feature Fusion via Network Architecture Search for Classification of Multimodal Remote Sensing Images},
author = {Shiyang Feng and Zhaowei Li and Bo Zhang and Tao Chen},
url = {https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=10904332},
year = {2025},
date = {2025-03-01},
urldate = {2025-03-01},
journal = { IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. },
keywords = {},
pubstate = {published},
tppubtype = {article}
}
4018.
(Ed.)
TinyDevID: TinyML-Driven IoT Devices IDentification Using Network Flow Data Collection
2025.
@collection{Rushikesh-csp25a,
title = {TinyDevID: TinyML-Driven IoT Devices IDentification Using Network Flow Data},
author = {Priyanka Rushikesh Chaudhary and Anand Agrawal and Rajib Ranjan Maiti},
url = {https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=10885715},
year = {2025},
date = {2025-02-01},
urldate = {2025-02-01},
booktitle = {COMSNETS 2025 - Cybersecurity & Privacy Workshop (CSP)},
keywords = {},
pubstate = {published},
tppubtype = {collection}
}
4017.
Yu, Sixing
2025.
@phdthesis{yu-phd25a,
title = {Scalable and resource-efcient federated learning: Techniques for resource-constrained heterogeneous systems},
author = {Sixing Yu},
url = {https://www.proquest.com/docview/3165602177?pq-origsite=gscholar&fromopenview=true&sourcetype=Dissertations%20&%20Theses},
year = {2025},
date = {2025-02-01},
urldate = {2025-02-01},
keywords = {},
pubstate = {published},
tppubtype = {phdthesis}
}
4016.
Fu, Jintao; Cong, Peng; Xu, Shuo; Chang, Jiahao; Liu, Ximing; Sun, Yuewen
Neural architecture search with Deep Radon Prior for sparse-view CT image reconstruction Journal Article
In: Med Phys , 2025.
@article{Fu-medphs25a,
title = { Neural architecture search with Deep Radon Prior for sparse-view CT image reconstruction },
author = {Jintao Fu and Peng Cong and Shuo Xu and Jiahao Chang and Ximing Liu and Yuewen Sun
},
url = {https://pubmed.ncbi.nlm.nih.gov/39930320/},
year = {2025},
date = {2025-02-01},
urldate = {2025-02-01},
journal = { Med Phys },
keywords = {},
pubstate = {published},
tppubtype = {article}
}
4015.
Zhao, Yi-Heng; Pang, Shen-Wen; Huang, Heng-Zhi; Wu, Shao-Wen; Sun, Shao-Hua; Liu, Zhen-Bing; Pan, Zhi-Chao
Automatic clustering of single-molecule break junction data through task-oriented representation learning Journal Article
In: Rare Metals , 2025.
@article{zhao-rarem25a,
title = {Automatic clustering of single-molecule break junction data through task-oriented representation learning},
author = {
Yi-Heng Zhao and Shen-Wen Pang and Heng-Zhi Huang and Shao-Wen Wu and Shao-Hua Sun and Zhen-Bing Liu and Zhi-Chao Pan
},
url = {https://link.springer.com/article/10.1007/s12598-024-03089-7},
year = {2025},
date = {2025-02-01},
urldate = {2025-02-01},
journal = { Rare Metals },
keywords = {},
pubstate = {published},
tppubtype = {article}
}
4014.
Huang, Tao
Efficient Deep Neural Architecture Design and Training PhD Thesis
2025.
@phdthesis{nokey,
title = {Efficient Deep Neural Architecture Design and Training},
author = { Huang, Tao },
url = {https://ses.library.usyd.edu.au/handle/2123/33598},
year = {2025},
date = {2025-02-01},
urldate = {2025-02-01},
keywords = {},
pubstate = {published},
tppubtype = {phdthesis}
}
4013.
Herterich, Nils; Liu, Kai; Stein, Anthony
Multi-objective neural architecture search for real-time weed detection on embedded system Miscellaneous
2025.
@misc{Herterich,
title = {Multi-objective neural architecture search for real-time weed detection on embedded system},
author = {Nils Herterich and Kai Liu and Anthony Stein},
url = {https://dl.gi.de/server/api/core/bitstreams/29a49f8d-304e-4073-8a92-4bef6483c087/content},
year = {2025},
date = {2025-02-01},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
4012.
Tabak, Gabriel Couto; Molenaar, Dylan; Curi, Mariana
An evolutionary neural architecture search for item response theory autoencoders Journal Article
In: Behaviormetrika , 2025.
@article{nokey,
title = {An evolutionary neural architecture search for item response theory autoencoders},
author = {Gabriel Couto Tabak and Dylan Molenaar and Mariana Curi
},
url = {https://link.springer.com/article/10.1007/s41237-024-00250-5},
year = {2025},
date = {2025-01-27},
urldate = {2025-01-27},
journal = {Behaviormetrika },
keywords = {},
pubstate = {published},
tppubtype = {article}
}
4011.
Hao, Debei; Pei, Songwei
MIG-DARTS: towards effective differentiable architecture search by gradually mitigating the initial-channel gap between search and evaluation Journal Article
In: Neural Computing and Applications, 2025.
@article{nokey,
title = {MIG-DARTS: towards effective differentiable architecture search by gradually mitigating the initial-channel gap between search and evaluation},
author = {
Debei Hao and Songwei Pei
},
url = {https://link.springer.com/article/10.1007/s00521-024-10681-6},
year = {2025},
date = {2025-01-09},
urldate = {2025-01-09},
journal = {Neural Computing and Applications},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
4010.
(Ed.)
2025.
@collection{nokey,
title = {H4H: Hybrid Convolution-Transformer Architecture Search for NPU-CIM Heterogeneous Systems for AR/VR Applications},
author = {Yiwei Zhao and Jinhui Chen and Sai Qian Zhang and Syed Shakib Sarwar and Kleber Hugo Stangherlin and Jorge Tomas Gomez and Jae-Sun Seo and Barbara De Salvo and Chiao Liu and Phillip B. Gibbons and Ziyun Li},
url = {https://www.pdl.cmu.edu/PDL-FTP/associated/ASP-DAC2025-1073-12.pdf},
year = {2025},
date = {2025-01-02},
urldate = {2025-01-02},
booktitle = {ASPDAC ’25},
keywords = {},
pubstate = {published},
tppubtype = {collection}
}
4009.
Li, Kai; Huang, Mingqiang; Li, Ang; Yang, Shuxin; Cheng, Quan; Yu, Hao
A 29.12-TOPS/W Vector Systolic Accelerator With NAS-Optimized DNNs in 28-nm CMOS Journal Article
In: IEEE Journal of Solid-State Circuits, pp. 1-12, 2025.
@article{10972309,
title = {A 29.12-TOPS/W Vector Systolic Accelerator With NAS-Optimized DNNs in 28-nm CMOS},
author = {Kai Li and Mingqiang Huang and Ang Li and Shuxin Yang and Quan Cheng and Hao Yu},
url = {https://ieeexplore.ieee.org/abstract/document/10972309},
doi = {10.1109/JSSC.2025.3558287},
year = {2025},
date = {2025-01-01},
urldate = {2025-01-01},
journal = {IEEE Journal of Solid-State Circuits},
pages = {1-12},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
4008.
Mecharbat, Lotfi Abdelkrim; Almakky, Ibrahim; Takac, Martin; Yaqub, Mohammad
MedNNS: Supernet-based Medical Task-Adaptive Neural Network Search Technical Report
2025.
@techreport{mecharbat2025mednnssupernetbasedmedicaltaskadaptive,
title = {MedNNS: Supernet-based Medical Task-Adaptive Neural Network Search},
author = {Lotfi Abdelkrim Mecharbat and Ibrahim Almakky and Martin Takac and Mohammad Yaqub},
url = {https://arxiv.org/abs/2504.15865},
year = {2025},
date = {2025-01-01},
urldate = {2025-01-01},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
4007.
Liu, Wenbo; Wu, Jia; Deng, Tao; Yan, Fei
Continuous–Discrete Alignment Optimization for efficient differentiable neural architecture search Journal Article
In: Engineering Applications of Artificial Intelligence, vol. 153, pp. 110721, 2025, ISSN: 0952-1976.
@article{LIU2025110721,
title = {Continuous–Discrete Alignment Optimization for efficient differentiable neural architecture search},
author = {Wenbo Liu and Jia Wu and Tao Deng and Fei Yan},
url = {https://www.sciencedirect.com/science/article/pii/S0952197625007213},
doi = {https://doi.org/10.1016/j.engappai.2025.110721},
issn = {0952-1976},
year = {2025},
date = {2025-01-01},
urldate = {2025-01-01},
journal = {Engineering Applications of Artificial Intelligence},
volume = {153},
pages = {110721},
abstract = {Differential Architecture Search (DARTS) has become a prominent technique for neural architecture search in recent years. Despite its merits, the issue of discretization discrepancy within DARTS still necessitates further exploration, as it can degrade in performance. In this paper, we introduce a novel algorithm termed Continuous–Discrete Alignment Optimization (DARTS-CDAO), designed to address the discretization discrepancy and thereby enhance the robustness and generalization capabilities of the discovered neural architectures. Our proposed DARTS-CDAO algorithm seamlessly integrates the discretization process into the training phase of the architecture parameters, thereby bolstering the search algorithm’s adaptability to the inherent discretization processes. Specifically, our methodology commences by formalizing the process of architecture parameter discretization. Subsequently, we introduce a coarse gradient weighting algorithm that is employed to update the architecture parameters, effectively minimizing the divergence between the representation of continuous and discrete parameters. Rigorous theoretical analysis, coupled with extensive experimental outcomes, substantiates that our proposed approach can elevate the performance of the searched models. Notably, this enhancement is achieved without incurring additional search time, rendering DARTS more robust and endowed with a heightened capacity for generalization.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Differential Architecture Search (DARTS) has become a prominent technique for neural architecture search in recent years. Despite its merits, the issue of discretization discrepancy within DARTS still necessitates further exploration, as it can degrade in performance. In this paper, we introduce a novel algorithm termed Continuous–Discrete Alignment Optimization (DARTS-CDAO), designed to address the discretization discrepancy and thereby enhance the robustness and generalization capabilities of the discovered neural architectures. Our proposed DARTS-CDAO algorithm seamlessly integrates the discretization process into the training phase of the architecture parameters, thereby bolstering the search algorithm’s adaptability to the inherent discretization processes. Specifically, our methodology commences by formalizing the process of architecture parameter discretization. Subsequently, we introduce a coarse gradient weighting algorithm that is employed to update the architecture parameters, effectively minimizing the divergence between the representation of continuous and discrete parameters. Rigorous theoretical analysis, coupled with extensive experimental outcomes, substantiates that our proposed approach can elevate the performance of the searched models. Notably, this enhancement is achieved without incurring additional search time, rendering DARTS more robust and endowed with a heightened capacity for generalization.
4006.
Zhang, Ruohan; Li, Lingling; Jiao, Licheng; Liu, Fang; Liu, Xu; Yang, Shuyuan
Knowledge-Aware Evolutionary Transformer Journal Article
In: IEEE Transactions on Evolutionary Computation, pp. 1-1, 2025.
@article{10970744,
title = {Knowledge-Aware Evolutionary Transformer},
author = {Ruohan Zhang and Lingling Li and Licheng Jiao and Fang Liu and Xu Liu and Shuyuan Yang},
url = {https://ieeexplore.ieee.org/document/10970744},
doi = {10.1109/TEVC.2025.3562576},
year = {2025},
date = {2025-01-01},
urldate = {2025-01-01},
journal = {IEEE Transactions on Evolutionary Computation},
pages = {1-1},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
4005.
Zhao, Yunbiao; Wang, Lei; Wu, Jiang; Li, Taiyong
NAST: neural architecture search and transformer for image manipulation localization Journal Article
In: Journal of Electronic Imaging, vol. 34, no. 2, pp. 023057, 2025.
@article{10.1117/1.JEI.34.2.023057,
title = {NAST: neural architecture search and transformer for image manipulation localization},
author = {Yunbiao Zhao and Lei Wang and Jiang Wu and Taiyong Li},
url = {https://doi.org/10.1117/1.JEI.34.2.023057},
doi = {10.1117/1.JEI.34.2.023057},
year = {2025},
date = {2025-01-01},
urldate = {2025-01-01},
journal = {Journal of Electronic Imaging},
volume = {34},
number = {2},
pages = {023057},
publisher = {SPIE},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
4004.
Mohasel, Seyed Mojtaba; Sheppard, John; Molina, Lindsey K.; Neptune, Richard R.; Wurdeman, Shane R.; Pew, Corey A.
MicroNAS: An Automated Framework for Developing a Fall Detection System Technical Report
2025.
@techreport{mohasel2025micronasautomatedframeworkdevelopingb,
title = {MicroNAS: An Automated Framework for Developing a Fall Detection System},
author = {Seyed Mojtaba Mohasel and John Sheppard and Lindsey K. Molina and Richard R. Neptune and Shane R. Wurdeman and Corey A. Pew},
url = {https://arxiv.org/abs/2504.07397},
year = {2025},
date = {2025-01-01},
urldate = {2025-01-01},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
4003.
Lu, Xiaotong; Dong, Weisheng; Fang, Zhenxuan; Lin, Jie; Li, Xin; Shi, Guangming
Growing-before-pruning: A progressive neural architecture search strategy via group sparsity and deterministic annealing Journal Article
In: Pattern Recognition, vol. 166, pp. 111697, 2025, ISSN: 0031-3203.
@article{LU2025111697,
title = {Growing-before-pruning: A progressive neural architecture search strategy via group sparsity and deterministic annealing},
author = {Xiaotong Lu and Weisheng Dong and Zhenxuan Fang and Jie Lin and Xin Li and Guangming Shi},
url = {https://www.sciencedirect.com/science/article/pii/S0031320325003577},
doi = {https://doi.org/10.1016/j.patcog.2025.111697},
issn = {0031-3203},
year = {2025},
date = {2025-01-01},
urldate = {2025-01-01},
journal = {Pattern Recognition},
volume = {166},
pages = {111697},
abstract = {Network pruning is a widely studied technique of obtaining compact representations from over-parameterized deep convolutional neural networks. Existing pruning methods are based on finding an optimal combination of pruned filters in the fixed search space. However, the optimality of those methods is often questionable due to limited search space and pruning choices - e.g., the difficulty with removing the entire layer and the risk of unexpected performance degradation. Inspired by the exploration vs. exploitation trade-off in reinforcement learning, we propose to reconstruct the filter space without increasing the model capacity and prune them by exploiting group sparsity. Our approach challenges the conventional wisdom by advocating the strategy of Growing-before-Pruning (GbP), which allows us to explore more space before exploiting the power of architecture search. Meanwhile, to achieve more efficient pruning, we propose to measure the importance of filters by global group sparsity, which extends the existing Gaussian scale mixture model. Such global characterization of sparsity in the filter space leads to a novel deterministic annealing strategy for progressively pruning the filters. We have evaluated our method on several popular datasets and network architectures. Our extensive experiment results have shown that the proposed method advances the current state-of-the-art.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Network pruning is a widely studied technique of obtaining compact representations from over-parameterized deep convolutional neural networks. Existing pruning methods are based on finding an optimal combination of pruned filters in the fixed search space. However, the optimality of those methods is often questionable due to limited search space and pruning choices - e.g., the difficulty with removing the entire layer and the risk of unexpected performance degradation. Inspired by the exploration vs. exploitation trade-off in reinforcement learning, we propose to reconstruct the filter space without increasing the model capacity and prune them by exploiting group sparsity. Our approach challenges the conventional wisdom by advocating the strategy of Growing-before-Pruning (GbP), which allows us to explore more space before exploiting the power of architecture search. Meanwhile, to achieve more efficient pruning, we propose to measure the importance of filters by global group sparsity, which extends the existing Gaussian scale mixture model. Such global characterization of sparsity in the filter space leads to a novel deterministic annealing strategy for progressively pruning the filters. We have evaluated our method on several popular datasets and network architectures. Our extensive experiment results have shown that the proposed method advances the current state-of-the-art.
4002.
Saha, Bidyut; Samanta, Riya; Roy, Ram Babu; Ghosh, Soumya K.
TinyTNAS: Time-Bound, GPU-Independent Hardware-Aware Neural Architecture Search for TinyML Time Series Classification Journal Article
In: IEEE Embedded Systems Letters, pp. 1-1, 2025.
@article{10967537,
title = {TinyTNAS: Time-Bound, GPU-Independent Hardware-Aware Neural Architecture Search for TinyML Time Series Classification},
author = {Bidyut Saha and Riya Samanta and Ram Babu Roy and Soumya K. Ghosh},
url = {https://ieeexplore.ieee.org/abstract/document/10967537},
doi = {10.1109/LES.2025.3561870},
year = {2025},
date = {2025-01-01},
urldate = {2025-01-01},
journal = {IEEE Embedded Systems Letters},
pages = {1-1},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
4001.
Liu, Zhi-Ang; Liu, Jiang-Jiang
Towards efficient salient object detection via U-shape architecture search Journal Article
In: Knowledge-Based Systems, vol. 318, pp. 113515, 2025, ISSN: 0950-7051.
@article{LIU2025113515,
title = {Towards efficient salient object detection via U-shape architecture search},
author = {Zhi-Ang Liu and Jiang-Jiang Liu},
url = {https://www.sciencedirect.com/science/article/pii/S0950705125005611},
doi = {https://doi.org/10.1016/j.knosys.2025.113515},
issn = {0950-7051},
year = {2025},
date = {2025-01-01},
urldate = {2025-01-01},
journal = {Knowledge-Based Systems},
volume = {318},
pages = {113515},
abstract = {State-of-the-art (SOTA) deep learning architectures for salient object detection (SOD) are predominantly handcrafted, with many methods adapting successful classification backbones for SOD tasks. In this work, we aim to design more efficient architectures specifically tailored for SOD, accommodating both RGB and RGB-D input modalities. Leveraging neural architecture search (NAS), we uncover unique characteristics of SOD by proposing a novel U-shaped search space. This design integrates bottom-up and top-down pathways, enhanced by interconnecting links between them. To further optimize the complexity distribution across these pathways, we introduce a per-complexity importance measure. The resulting architectures, NASAL and NASAL-D (targeting RGB and RGB-D SOD, respectively), achieve an improved trade-off between accuracy and computational efficiency. Extensive experiments on multiple popular benchmarks demonstrate that our models consistently outperform existing methods in both effectiveness and efficiency.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
State-of-the-art (SOTA) deep learning architectures for salient object detection (SOD) are predominantly handcrafted, with many methods adapting successful classification backbones for SOD tasks. In this work, we aim to design more efficient architectures specifically tailored for SOD, accommodating both RGB and RGB-D input modalities. Leveraging neural architecture search (NAS), we uncover unique characteristics of SOD by proposing a novel U-shaped search space. This design integrates bottom-up and top-down pathways, enhanced by interconnecting links between them. To further optimize the complexity distribution across these pathways, we introduce a per-complexity importance measure. The resulting architectures, NASAL and NASAL-D (targeting RGB and RGB-D SOD, respectively), achieve an improved trade-off between accuracy and computational efficiency. Extensive experiments on multiple popular benchmarks demonstrate that our models consistently outperform existing methods in both effectiveness and efficiency.
4000.
Qin, Shiwen; Kadlecová, Gabriela; Pilát, Martin; Cohen, Shay B.; Neruda, Roman; Crowley, Elliot J.; Lukasik, Jovita; Ericsson, Linus
Transferrable Surrogates in Expressive Neural Architecture Search Spaces Technical Report
2025.
@techreport{qin2025transferrablesurrogatesexpressiveneural,
title = {Transferrable Surrogates in Expressive Neural Architecture Search Spaces},
author = {Shiwen Qin and Gabriela Kadlecová and Martin Pilát and Shay B. Cohen and Roman Neruda and Elliot J. Crowley and Jovita Lukasik and Linus Ericsson},
url = {https://arxiv.org/abs/2504.12971},
year = {2025},
date = {2025-01-01},
urldate = {2025-01-01},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
3999.
Carstensen, Timur; Mallik, Neeratyoy; Hutter, Frank; Rapp, Martin
Frozen Layers: Memory-efficient Many-fidelity Hyperparameter Optimization Technical Report
2025.
@techreport{carstensen2025frozenlayersmemoryefficientmanyfidelity,
title = {Frozen Layers: Memory-efficient Many-fidelity Hyperparameter Optimization},
author = {Timur Carstensen and Neeratyoy Mallik and Frank Hutter and Martin Rapp},
url = {https://arxiv.org/abs/2504.10735},
year = {2025},
date = {2025-01-01},
urldate = {2025-01-01},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
3998.
Ahsun, Abbas; Noah, Asher; John, Ada
Building intelligent systems that can automatically generate tailored algorithms for specific application areas Technical Report
2025.
@techreport{articlek,
title = {Building intelligent systems that can automatically generate tailored algorithms for specific application areas},
author = {Abbas Ahsun and Asher Noah and Ada John},
url = {https://www.researchgate.net/publication/390805745_Building_intelligent_systems_that_can_automatically_generate_tailored_algorithms_for_specific_application_areas},
year = {2025},
date = {2025-01-01},
urldate = {2025-01-01},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}