AutoML | Literature on Neural Architecture Search

3488.

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.

Abstract | Links | BibTeX

3487.

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.

Abstract | Links | BibTeX

@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}

}

Close

3486.

Ouertatani, Houssem; Maxim, Cristian; Niar, Smail; Talbi, El-Ghazali

Accelerated NAS via pretrained ensembles and multi-fidelity Bayesian Optimization Proceedings Article

In: 33rd International Conference on Artificial Neural Networks (ICANN), Lugano, Switzerland, 2024.

Links | BibTeX

3485.

(Ed.)

Medical Neural Architecture Search: Survey and Taxonomy Collection

2024.

Links | BibTeX

3484.

(Ed.)

A COMPARATIVE STUDY: DEEPFAKE VIDEO DETECTION WITH NASNETS AND LSTM Collection

2024.

Links | BibTeX

3483.

Ge, Wanying

Spoofing-robust Automatic Speaker Verification: Architecture, Explainability and Joint Optimisation PhD Thesis

2024.

Links | BibTeX

3482.

Hosseini, Ramtin

Trustworthy Neural Architecture Search PhD Thesis

2024.

Links | BibTeX

3481.

Huang, Chien Yu; Tsai, Cheng-Che; Hwang, Lisa Alice; Kang, Bor-Hwang; Lin, Yaoh-Shiang; Su, Hsing-Hao; Shen, Guan‐Ting; Hsieh, Jun-Wei

SCC-NET: Segmentation of Clinical Cancer image for Head and Neck Squamous Cell Carcinoma Technical Report

2024.

Links | BibTeX

3480.

Asiimwe, Arnold; Das, William; Benmeziane, Hadjer; Maghraoui, Kaoutar El

EfficientMedSAM: Accelerating Medical Image Segmentation via Neural Architecture Search and Knowledge Distillation Conference

EDGE2024, 2024.

Links | BibTeX

3479.

(Ed.)

Are Large Language Models Good Neural Architecture Generators for Edge? Collection

2024.

Links | BibTeX

3478.

Yin, Jia; Wang, Wei; Guo, Zhonghua; Ji, Yangchun

DTS: dynamic training slimming with feature sparsity for efficient convolutional neural network Journal Article

In: Journal of Real-Time Image Processing, 2024.

Links | BibTeX

3477.

(Ed.)

Neural Architecture Search for Adversarial Robustness via Learnable Pruning Collection

2024.

Links | BibTeX

3476.

Yang, Jiechao; Liu, Yong

ETAS: Zero-Shot Transformer Architecture Search via Network Trainability and Expressivity Miscellaneous

2024.

Links | BibTeX

3475.

(Ed.)

UP-NAS: Unified Proxy for Neural Architecture Search Collection

2024.

Links | BibTeX

3474.

Wang, Xin; Chen, Hong; Pan, Zirui; Zhou, Yuwei; Guan, Chaoyu; Sun, Lifeng; Zhu, Wenwu

Automated Disentangled Sequential Recommendation with Large Language Models Journal Article

In: ACM Trans. Inf. Syst., 2024, ISSN: 1046-8188, (Just Accepted).

Abstract | Links | BibTeX

@article{10.1145/3675164,

title = {Automated Disentangled Sequential Recommendation with Large Language Models},

author = {Xin Wang and Hong Chen and Zirui Pan and Yuwei Zhou and Chaoyu Guan and Lifeng Sun and Wenwu Zhu},

url = {https://doi.org/10.1145/3675164},

doi = {10.1145/3675164},

issn = {1046-8188},

year  = {2024},

date = {2024-06-01},

urldate = {2024-06-01},

journal = {ACM Trans. Inf. Syst.},

publisher = {Association for Computing Machinery},

address = {New York, NY, USA},

abstract = {Sequential recommendation aims to recommend the next items that a target user may have interest in based on the user’s sequence of past behaviors, which has become a hot research topic in both academia and industry. In the literature, sequential recommendation adopts a Sequence-to-Item or Sequence-to-Sequence training strategy, which supervises a sequential model with a user’s next one or more behaviors as the labels and the sequence of the past behaviors as the input. However, existing powerful sequential recommendation approaches employ more and more complex deep structures such as Transformer in order to accurately capture the sequential patterns, which heavily rely on hand-crafted designs on key attention mechanism to achieve state-of-the-art performance, thus failing to automatically obtain the optimal design of attention representation architectures in various scenarios with different data. Other works on classic automated deep recommender systems only focus on traditional settings, ignoring the problem of sequential scenarios. In this paper, we study the problem of automated sequential recommendation, which faces two main challenges: i) How can we design a proper search space tailored for attention automation in sequential recommendation, and ii) How can we accurately search effective attention representation architectures considering multiple user interests reflected in the sequential behavior. To tackle these challenges, we propose an automated disentangled sequential recommendation (AutoDisenSeq) model. In particular, we employ neural architecture search (NAS) and design a search space tailored for automated attention representation in attentive intention-disentangled sequential recommendation with an expressive and efficient space complexity of (O(n^2)) given (n) as the number of layers. We further propose a context-aware parameter sharing mechanism taking characteristics of each sub-architecture into account to enable accurate architecture performance estimations and great flexibility for disentanglement of latent intention representation. Moreover, we propose AutoDisenSeq-LLM, which utilizes the textual understanding power of large language model (LLM) as a guidance to refine the candidate list for recommendation from AutoDisenSeq. We conduct extensive experiments to show that our proposed AutoDisenSeq model and AutoDisenSeq-LLM model outperform existing baseline methods on four real-world datasets in both overall recommendation and cold-start recommendation scenarios.},

note = {Just Accepted},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

Close

Sequential recommendation aims to recommend the next items that a target user may have interest in based on the user’s sequence of past behaviors, which has become a hot research topic in both academia and industry. In the literature, sequential recommendation adopts a Sequence-to-Item or Sequence-to-Sequence training strategy, which supervises a sequential model with a user’s next one or more behaviors as the labels and the sequence of the past behaviors as the input. However, existing powerful sequential recommendation approaches employ more and more complex deep structures such as Transformer in order to accurately capture the sequential patterns, which heavily rely on hand-crafted designs on key attention mechanism to achieve state-of-the-art performance, thus failing to automatically obtain the optimal design of attention representation architectures in various scenarios with different data. Other works on classic automated deep recommender systems only focus on traditional settings, ignoring the problem of sequential scenarios. In this paper, we study the problem of automated sequential recommendation, which faces two main challenges: i) How can we design a proper search space tailored for attention automation in sequential recommendation, and ii) How can we accurately search effective attention representation architectures considering multiple user interests reflected in the sequential behavior. To tackle these challenges, we propose an automated disentangled sequential recommendation (AutoDisenSeq) model. In particular, we employ neural architecture search (NAS) and design a search space tailored for automated attention representation in attentive intention-disentangled sequential recommendation with an expressive and efficient space complexity of (O(n^2)) given (n) as the number of layers. We further propose a context-aware parameter sharing mechanism taking characteristics of each sub-architecture into account to enable accurate architecture performance estimations and great flexibility for disentanglement of latent intention representation. Moreover, we propose AutoDisenSeq-LLM, which utilizes the textual understanding power of large language model (LLM) as a guidance to refine the candidate list for recommendation from AutoDisenSeq. We conduct extensive experiments to show that our proposed AutoDisenSeq model and AutoDisenSeq-LLM model outperform existing baseline methods on four real-world datasets in both overall recommendation and cold-start recommendation scenarios.

Close

3473.

(Ed.)

On Efficient Object-Detection NAS for ADAS on Edge devices Collection

2024.

Links | BibTeX

3472.

Micheal, A Ancy; Micheal, A Annie; Gopinathan, Anurekha; Barath, B U Anu

Deep Learning-based Multi-class Object Tracking With Occlusion Handling Mechanism in Uav Videos Technical Report

2024.

Links | BibTeX

3471.

(Ed.)

Disentangled Continual Graph Neural Architecture Search with Invariant Modular Supernet Collection

2024.

Links | BibTeX

3470.

Gao, Tianxiao; Guo, Li; Zhao, Shanwei; Xu, Peihan; Yang, Yukun; Liu, Xionghao; Wang, Shihao; Zhu, Shiai; Zhou, Dajiang

QuantNAS: Quantization-aware Neural Architecture Search For Efficient Deployment On Mobile Device Proceedings Article

In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 1704-1713, 2024.

Links | BibTeX

3469.

(Ed.)

Agent Based Model for AUTODL Optimisation Collection

2024.

Links | BibTeX

3468.

Wang, Zixiao; Wang, Jiansu; Li, Shuo; Yang, Jiadi; Xing, Tianzhang

A lightweight and real-time responsive framework for various visual tasks via neural architecture search Journal Article

In: CCF Transactions on Pervasive Computing and Interaction , 2024.

Links | BibTeX

3467.

Krestinskaya, Olga; Fouda, Mohammed E.; Benmeziane, Hadjer; Maghraoui, Kaoutar El; Sebastian, Abu; Lu, Wei D.; Lanza, Mario; Li, Hai; Kurdahi, Fadi; Fahmy, Suhaib A.; Eltawil, Ahmed; Salama, Khaled N.

Neural architecture search for in-memory computing-based deep learning accelerators Journal Article

In: nature reviews electrical engineering , pp. 374-390, 2024.

Links | BibTeX

3466.

Venske, Sandra Mara Scós; de Almeida, Carolina Paula; Delgado, Myriam Regattieri

Metaheuristics and machine learning: an approach with reinforcement learning assisting neural architecture search Journal Article

In: Journal of Heuristics, 2024.

Links | BibTeX

3465.

Mengyan Jin Jianfang Cao, Yun Tian

Ancient mural dynasty recognition algorithm based on a neural network architecture search Journal Article

In: Heritage Science , 2024.

Links | BibTeX

3464.

Ramaraj, N.; Murugan, G.; Regunathan, R.

Neural Network-Powered Conductorless Ticketing for Public Transportation Proceedings Article

In: 2024 4th International Conference on Pervasive Computing and Social Networking (ICPCSN), pp. 236-241, IEEE Computer Society, Los Alamitos, CA, USA, 2024.

Abstract | Links | BibTeX

3463.

Porta, Alessandro Benfenati Ambra Catozzi Giorgia Franchini Federica

Early stopping strategies in Deep Image Prior Technical Report

2024.

Links | BibTeX

3462.

Lee, Matthew; Sanchez-Matilla, Ricardo; Stoyanov, Danail; Luengo, Imanol

DIPO: Differentiable Parallel Operation Blocks for Surgical Neural Architecture Search Journal Article

In: IEEE J Biomed Health Inform , 2024.

Links | BibTeX

3461.

Li, Guilin; Wang, Qiang; Zheng, Xiawu

Distilling Structural Knowledge for Platform-Aware Semantic Segmentation Journal Article

In: Journal of Physics: Conference Series, vol. 2759, no. 1, pp. 012010, 2024.

Abstract | Links | BibTeX

@article{Li_2024,

title = {Distilling Structural Knowledge for Platform-Aware Semantic Segmentation},

author = {Guilin Li and Qiang Wang and Xiawu Zheng},

url = {https://dx.doi.org/10.1088/1742-6596/2759/1/012010},

doi = {10.1088/1742-6596/2759/1/012010},

year  = {2024},

date = {2024-05-01},

urldate = {2024-05-01},

journal = {Journal of Physics: Conference Series},

volume = {2759},

number = {1},

pages = {012010},

publisher = {IOP Publishing},

abstract = {Knowledge Distillation (KD) aims to distill the dark knowledge of a high-powered teacher network into a student network, which can improve the capacity of student network and has been successfully applied to semantic segmentation. However, the standard knowledge distillation approaches merely represent the supervisory signal of teacher network as the dark knowledge, while ignoring the impact of network architecture during distillation. In this paper, we found that the student network with a more similar architecture against the teacher network obtains more performance gain from distillation. Therefore, a more generalized paradigm for knowledge distillation is to distill both the soft-label and the structure of the teacher network. We propose a novel Structural Distillation (SD) method which introduces the structural similarity constraints into vanilla knowledge distillation. We leverage Neural Architecture Search technique to search optimal student structure for semantic segmentation from a well-designed search space, which mimics the given teacher both in terms of soft-label and network structure. Experiment results make clear that our proposed method outperforms both the NAS with conventional Knowledge Distillation and human-designed methods, and achieves sota performance on the Cityscapes dataset under various platform-aware latency constraints. Furthermore, the best architecture discovered on Cityscapes also transfers well to the PASCAL VOC2012 dataset.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

Close

3460.

(Ed.)

SCAN-EDGE: FINDING MOBILENET-SPEED HYBRID NETWORKS FOR COMMODITY EDGE DEVICES Collection

2024.

Links | BibTeX

3459.

Wang, Gang; Wang, Bang-Hai; Fei, Shao-Ming

An RNN–policy gradient approach for quantum architecture search Journal Article

In: Quantum Information Processing, vol. 23, no. 5, 2024, ISSN: 1573-1332.

Links | BibTeX

3458.

Gündüz, Hüseyin Anil; Mreches, René; Moosbauer, Julia; Robertson, Gary; To, Xiao-Yin; Franzosa, Eric A.; Huttenhower, Curtis; Rezaei, Mina; McHardy, Alice C.; Bischl, Bernd; Münch, Philipp C.; Binder, Martin

Optimized model architectures for deep learning on genomic data Journal Article

In: communications biology , 2024.

Links | BibTeX