AutoML | Literature on Neural Architecture Search

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).

Abstract | Links | BibTeX

@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}

}

Close

4136.

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.

Links | BibTeX

4135.

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.

Links | BibTeX

4134.

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.

Links | BibTeX

4133.

HERNANDEZ, ESAU ALAIN HERVERT; CAO, YAN; KEHTARNAVAZ, NASSER

Computationally Efficient Neural Architecture Search for Image Denoising Bachelor Thesis

2025.

Links | BibTeX

4132.

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.

Links | BibTeX

4131.

Xu, Dikai; Cao, Bin

Adaptive Multiobjective Evolutionary Generative Adversarial Network for Metaverse Network Intrusion Detection Journal Article

In: Science Partner Journals, 2025.

Links | BibTeX

4130.

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.

Links | BibTeX

4129.

(Ed.)

HPE-DARTS: Hybrid Pruning and Proxy Evaluation in Differentiable Architecture Search Collection

2025.

Links | BibTeX

4128.

(Ed.)

OPTIMIZED LSTM NEURAL NETWORKS VIA NEURAL ARCHITECTURE SEARCH FOR PREDICTING DAMAGE EVOLUTION IN COMPOSITE LAMINATES Collection

2025.

Links | BibTeX

4127.

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.

Links | BibTeX

4126.

(Ed.)

Neural Architecture Search: Tradeoff Between Performance and Efficiency Collection

2025.

Links | BibTeX

4125.

(Ed.)

PQNAS: Mixed-precision Quantization-aware Neural Architecture Search with Pseudo Quantizer Collection

2025.

Links | BibTeX

4124.

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.

Links | BibTeX

4123.

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.

Links | BibTeX

4122.

(Ed.)

TinyDevID: TinyML-Driven IoT Devices IDentification Using Network Flow Data Collection

2025.

Links | BibTeX

4121.

Yu, Sixing

Scalable and resource-efcient federated learning: Techniques for resource-constrained heterogeneous systems PhD Thesis

2025.

Links | BibTeX

4120.

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.

Links | BibTeX

4119.

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.

Links | BibTeX

4118.

Huang, Tao

Efficient Deep Neural Architecture Design and Training PhD Thesis

2025.

Links | BibTeX

4117.

Herterich, Nils; Liu, Kai; Stein, Anthony

Multi-objective neural architecture search for real-time weed detection on embedded system Miscellaneous

2025.

Links | BibTeX

4116.

Tabak, Gabriel Couto; Molenaar, Dylan; Curi, Mariana

An evolutionary neural architecture search for item response theory autoencoders Journal Article

In: Behaviormetrika , 2025.

Links | BibTeX

4115.

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.

Links | BibTeX

4114.

(Ed.)

H4H: Hybrid Convolution-Transformer Architecture Search for NPU-CIM Heterogeneous Systems for AR/VR Applications Collection

2025.

Links | BibTeX

4113.

Shu, Xin; Niu, Mengxuan; Zhang, Yi; Luo, Wei; Zhou, Renjie

Neural Architecture Search Generated Phase Retrieval Net for Real-Time Off-Axis Quantitative Phase Imaging Journal Article

In: IEEE Photonics Technology Letters, vol. 37, no. 18, pp. 1069-1072, 2025.

Links | BibTeX

4112.

Rajeev, Shreyas; Babu, B Sathish

Finding Optimal Kernel Size and Dimension in Convolutional Neural Networks An Architecture Optimization Approach Technical Report

2025.

Links | BibTeX

4111.

Xu, Jingjing; Yang, Zijian; Zeyer, Albert; Beck, Eugen; Schlueter, Ralf; Ney, Hermann

Dynamic Acoustic Model Architecture Optimization in Training for ASR Technical Report

2025.

Links | BibTeX

4110.

Han, Honggui; Zhang, Qiyu; Li, Fangyu; Du, Yongping

Exploiting long-term markovian feature importance via dual attention for partially-connected differential architecture search Journal Article

In: Engineering Applications of Artificial Intelligence, vol. 158, pp. 111476, 2025, ISSN: 0952-1976.

Abstract | Links | BibTeX

@article{HAN2025111476,

title = {Exploiting long-term markovian feature importance via dual attention for partially-connected differential architecture search},

author = {Honggui Han and Qiyu Zhang and Fangyu Li and Yongping Du},

url = {https://www.sciencedirect.com/science/article/pii/S0952197625014782},

doi = {https://doi.org/10.1016/j.engappai.2025.111476},

issn = {0952-1976},

year  = {2025},

date = {2025-01-01},

urldate = {2025-01-01},

journal = {Engineering Applications of Artificial Intelligence},

volume = {158},

pages = {111476},

abstract = {—Differentiable architecture search (DARTS) is implemented as a gradient-based search method for neural architecture generation. However, DARTS suffers from unbalanced competition between unweighted and weighted operations in the search phase of the supernetwork, resulting in a collapse of the search architecture. In this paper, exploiting long-term markovian feature importance via dual attention for partially-connected differential architecture search (MA-DARTS) is proposed, to overcome the excessive accumulation of unweighted operation dominance by reducing redundant features in the supernetwork. First, spatial location attention factors for different semantic groups are learned through spatial attention. The grouped attention approach contributes to capture changes in the spatial semantic importance of search features. Secondly, the channel feature importance is obtained by learning channel attention weights without dimensionality reduction through a one-dimensional convolution factor. Finally, a Markov chain-based long-term importance feature channel selection strategy is designed. This strategy dynamically transmits key features to the search space, which improves the utilization of effective feature information in search. The experimental results demonstrate that MA-DARTS effectively suppresses the problem of excessive proportion of unweighted operations during the search process, achieving better network performance while ensuring the stability of the architecture search. Meanwhile, the proposed method achieves 0.43 %, 0.68 % and 2.2 % accuracy improvement compared to DARTS on Canadian institute for advanced research CIFAR-10, CIFAR-100 and ImageNet datasets.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

Close

4109.

Matthew, Bamidele; Pezzè, Mauro; Abrahão, Silvia; Penzenstadler, Birgit; mandal, Ashis; Nadim, Md; Schultz, Ulrik

Neural Architecture Search for AutoML in Healthcare Diagnostics: Customizing Models for Clinical Accuracy Journal Article

In: Journal of Healthcare Informatics Research, 2025.

Links | BibTeX

4108.

Fayyazi, Arya; Kamal, Mehdi; Pedram, Massoud

MARCO: Hardware-Aware Neural Architecture Search for Edge Devices with Multi-Agent Reinforcement Learning and Conformal Prediction Filtering Technical Report

2025.

Links | BibTeX

4107.

Yan, Renao

One-Shot Neural Architecture Search with Network Similarity Directed Initialization for Pathological Image Classification Technical Report

2025.

Links | BibTeX

4106.

Wang, Zhen; Zeng, Ruhao; Zhang, Hui; Chen, Tianyi

DeNoiseNAS: revisiting single-level optimization for efficient and stable neural architecture search Journal Article

In: Expert Systems with Applications, vol. 293, pp. 128649, 2025, ISSN: 0957-4174.

Abstract | Links | BibTeX

@article{WANG2025128649,

title = {DeNoiseNAS: revisiting single-level optimization for efficient and stable neural architecture search},

author = {Zhen Wang and Ruhao Zeng and Hui Zhang and Tianyi Chen},

url = {https://www.sciencedirect.com/science/article/pii/S0957417425022687},

doi = {https://doi.org/10.1016/j.eswa.2025.128649},

issn = {0957-4174},

year  = {2025},

date = {2025-01-01},

urldate = {2025-01-01},

journal = {Expert Systems with Applications},

volume = {293},

pages = {128649},

abstract = {Neural Architecture Search (NAS) has been an important topic to automate the designs of deep neural networks (DNNs). In this realm, differential NAS via multi-level optimization and zero-shot NAS are perhaps two most popular approaches. However, the existing methods typically suffer from balancing between search efficiency and stability. To address the dilemma, we revisit formulating the differentiable NAS as a single-level optimization problem and propose DeNoiseNAS to address the known coupling issue lying in single-level NAS paradigm. DeNoiseNAS employs a sophisticated search schema that establishes evaluation metrics through theoretical analysis of the neuron optimization process and progressively prunes based on these metrics to identify and remove redundant operators and noisy data samples. As a result, we achieve significant gains regarding search efficiency due to the pruning search space and dataset as well as sub-networks of higher performance due to the elimination of negative impacts from the noisy instances. Numerical experiments across extensive NAS benchmarks well validate the efficacy of DeNoiseNAS. In the DARTS and NAS-Bench-201, while maintaining a competitive search efficiency akin to zero-shot NAS, the architectures uncovered by our strategy surpass the existing state of the art in terms of accuracy, particularly on the ImageNet2012 dataset. In the AutoFormer benchmark, our method efficiently searches for high-performance architectures while consuming fewer resources.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

Close

4105.

Ayachi, Riadh; Afif, Mouna; Said, Yahia; Abdelali, Abdessalem Ben

Lightweight path aggregation network for pedestrian detection on FPGA board Journal Article

In: Journal of Parallel and Distributed Computing, vol. 204, pp. 105137, 2025, ISSN: 0743-7315.

Abstract | Links | BibTeX

@article{AYACHI2025105137,

title = {Lightweight path aggregation network for pedestrian detection on FPGA board},

author = {Riadh Ayachi and Mouna Afif and Yahia Said and Abdessalem Ben Abdelali},

url = {https://www.sciencedirect.com/science/article/pii/S0743731525001042},

doi = {https://doi.org/10.1016/j.jpdc.2025.105137},

issn = {0743-7315},

year  = {2025},

date = {2025-01-01},

urldate = {2025-01-01},

journal = {Journal of Parallel and Distributed Computing},

volume = {204},

pages = {105137},

abstract = {In urban environments, pedestrian safety stands as a pivotal metric dictating the accuracy and efficacy of cutting-edge technologies like Advanced Driver Assistance Systems (ADAS) and autonomous vehicles. However, the deployment of such technologies introduces various constraints, notably including the computational resources of processing boards. Therefore, constructing a robust pedestrian detection system necessitates achieving a delicate balance between performance and computational complexity. In this study, we propose the development of a lightweight Convolutional Neural Network (CNN) model specifically tailored for pedestrian detection. The backbone architecture of the model was meticulously searched using a network search engine predicated on the Multi-Objective Genetic Algorithm (NSGA-II) with a customized strategy. Notably, we shifted the search space from central processing units to Multi-Processor System-on-Chip (MPSoC) devices, aligning with the practical considerations of real-world applications. Our proposed model capitalizes on the path aggregation architecture coupled with a lightweight backbone design. The core concept revolves around the efficient transfer of high semantic features from the network's bottom to its top via the shortest path, thereby enhancing detection rates without introducing undue computational complexity. To ensure compatibility with embedded devices with limited memory, the proposed model underwent compression via quantization and pruning techniques. For rigorous evaluation, we tested the pedestrian detection model on the Xilinx ZCU 102 board, utilizing the Karlsruhe Institute of Technology and Toyota Technological Institute (KITTI) dataset for training and evaluation purposes. The reported results substantiate the efficacy of our proposed model, boasting a mean average precision (mAP) of 93.6 % alongside a commendable processing speed of 13 frames per second (FPS). These outcomes underscore the suitability of the proposed model for real-life scenarios, wherein ensuring a high level of safety remains paramount.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

Close

In urban environments, pedestrian safety stands as a pivotal metric dictating the accuracy and efficacy of cutting-edge technologies like Advanced Driver Assistance Systems (ADAS) and autonomous vehicles. However, the deployment of such technologies introduces various constraints, notably including the computational resources of processing boards. Therefore, constructing a robust pedestrian detection system necessitates achieving a delicate balance between performance and computational complexity. In this study, we propose the development of a lightweight Convolutional Neural Network (CNN) model specifically tailored for pedestrian detection. The backbone architecture of the model was meticulously searched using a network search engine predicated on the Multi-Objective Genetic Algorithm (NSGA-II) with a customized strategy. Notably, we shifted the search space from central processing units to Multi-Processor System-on-Chip (MPSoC) devices, aligning with the practical considerations of real-world applications. Our proposed model capitalizes on the path aggregation architecture coupled with a lightweight backbone design. The core concept revolves around the efficient transfer of high semantic features from the network's bottom to its top via the shortest path, thereby enhancing detection rates without introducing undue computational complexity. To ensure compatibility with embedded devices with limited memory, the proposed model underwent compression via quantization and pruning techniques. For rigorous evaluation, we tested the pedestrian detection model on the Xilinx ZCU 102 board, utilizing the Karlsruhe Institute of Technology and Toyota Technological Institute (KITTI) dataset for training and evaluation purposes. The reported results substantiate the efficacy of our proposed model, boasting a mean average precision (mAP) of 93.6 % alongside a commendable processing speed of 13 frames per second (FPS). These outcomes underscore the suitability of the proposed model for real-life scenarios, wherein ensuring a high level of safety remains paramount.

Close

4104.

Chehade, Adel; Ragusa, Edoardo; Gastaldo, Paolo; Zunino, Rodolfo

Efficient Traffic Classification using HW-NAS: Advanced Analysis and Optimization for Cybersecurity on Resource-Constrained Devices Technical Report

2025.

Links | BibTeX

4103.

Chehade, Adel; Ragusa, Edoardo; Gastaldo, Paolo; Zunino, Rodolfo

Energy-Efficient Deep Learning for Traffic Classification on Microcontrollers Miscellaneous

2025.

Links | BibTeX

4102.

Zhang, Xixi; Wang, Yu; Ohtsuki, Tomoaki; Gui, Guan; Yuen, Chau; Renzo, Marco Di; Sari, Hikmet

Malware Traffic Classification via Expandable Class Incremental Learning With Architecture Search Journal Article

In: IEEE Transactions on Information Forensics and Security, vol. 20, pp. 6074-6085, 2025.

Links | BibTeX

4101.

Oluremi, David

AutoML-Driven Architecture Search for Functional Genomics Prediction Using Deep Neural Networks Journal Article

In: 2025.

Links | BibTeX

4100.

Wang, Xiaofei; Zhao, Yunfeng; Qiu, Chao; Gao, Fei; Zhao, Zebo; Yao, Haipeng; Li, Xiuhua

Energy-Friendly Federated Neural Architecture Search for Industrial Cyber-Physical Systems Journal Article

In: IEEE Journal on Selected Areas in Communications, pp. 1-1, 2025.

Links | BibTeX

4099.

Hou, Libin; Wang, Linyuan; Hou, Senbao; Liu, Tianyuan; Ma, Shuxiao; Chen, Jian; Yan, Bin

Low redundancy cell-based Neural Architecture Search for large convolutional neural networks Journal Article

In: Neurocomputing, vol. 649, pp. 130644, 2025, ISSN: 0925-2312.

Abstract | Links | BibTeX

4098.

Huang, Zitong; Montazerin, Mansooreh; Srivastava, Ajitesh

SWAT-NN: Simultaneous Weights and Architecture Training for Neural Networks in a Latent Space Technical Report

2025.

Links | BibTeX

4097.

Kim, Jingeun; Yoon, Yourim

Pruning for efficient DenseNet via surrogate-model-assisted genetic algorithm considering neural architecture search proxies Journal Article

In: Swarm and Evolutionary Computation, vol. 97, pp. 101983, 2025, ISSN: 2210-6502.

Abstract | Links | BibTeX

@article{KIM2025101983,

title = {Pruning for efficient DenseNet via surrogate-model-assisted genetic algorithm considering neural architecture search proxies},

author = {Jingeun Kim and Yourim Yoon},

url = {https://www.sciencedirect.com/science/article/pii/S2210650225001415},

doi = {https://doi.org/10.1016/j.swevo.2025.101983},

issn = {2210-6502},

year  = {2025},

date = {2025-01-01},

urldate = {2025-01-01},

journal = {Swarm and Evolutionary Computation},

volume = {97},

pages = {101983},

abstract = {Recently, convolution neural networks have achieved remarkable progress in computer vision. These neural networks have a large number of parameters, which should be limited in resource-constrained environments. To address this problem, new pruning approaches have explored using neural architecture search (NAS) to determine optimal subnetworks. We propose a novel pruning framework using a surrogate model-assisted genetic algorithm considering NAS proxies (SMA-GA-NP). We applied multi-dimensional encoding and designed crossover and mutation methods. To reduce the search time of NAS, we leveraged a surrogate model to approximate the fitness value of individuals and used NAS proxies, such as reducing the number of epochs and the training set size. The DenseNet-BC (k = 12) model was used as the baseline. We achieved highly competitive performance on CIFAR-10 compared with other GA-based pruning methods and baselines. For CIFAR-100, we reduced the number of parameters by 11.25% to 18.75%, while achieving less than 1% performance degradation compared to the baseline model. These findings highlight SMA-GA-NP’s effectiveness in significantly reducing the number of parameters while having a negligible impact on the model’s performance. We also conducted an ablation study to explore the efficiency of the GA settings, the surrogate model, and NAS proxies in SMA-GA-NP and identified the current limitations and future potential of SMA-GA-NP.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}