Peng Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Peng Chen has a total of 92 co-authors. Here are the top co-authors by number of shared publications:
- Mohamed Wahib
RIKEN Center for Computational Science, Kobe, Japan
18 shared publications - Satoshi Matsuoka
RIKEN Center for Computational Science, Kobe, Japan and Institute of Science Tokyo, Tokyo, Japan
9 shared publications - Lingqi Zhang
RIKEN Center for Computational Science, Kobe, Japan
8 shared publications - Jintao Meng
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
7 shared publications - Toshio Endo
Institute of Science Tokyo
7 shared publications - Xiao Wang
Oak Ridge National Laboratory
7 shared publications
Latest Publications
- 4 November 2026
- Published by Elsevier in Information Sciences
- Vol. 766
TSD-diffusion: Timestep-aware two-stage neural architecture search and distillation for few-step diffusion generation
- 4 November 2026
- Published by Elsevier in Information Sciences
- Vol. 766
TSD-diffusion: Timestep-aware two-stage neural architecture search and distillation for few-step diffusion generation
- Open Access
- 5 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 422-435
SHIRO: Near-Optimal Communication Strategies for Distributed Sparse Matrix Multiplication
- 5 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 422-435
Open AccessSHIRO: Near-Optimal Communication Strategies for Distributed Sparse Matrix Multiplication
- 11 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive and Developmental Systems
- Vol. PP  (23798920) , 1-15
Surrogate-Assisted Neural Architecture Search with Performance Clustering
Evolutionary neural architecture search (ENAS) automates the design of neural network architectures but incurs significant computational costs during the evaluation phase of candidate neural networks in the evolutionary algorithm. To address this issue, surrogate models are widely adopted to estimate the performance of candidate architectures, thereby reducing resource consumption. However, existing surrogate models are primarily based on regression or classification. They are often hindered by interference from low-quality architectures, which limits search efficiency and final performance. To overcome these challenges, we propose surrogate-assisted neural architecture search with performance clustering (PCNAS). PCNAS introduces a contrastive learning-based performance clustering encoder (PCE). The PCE maps candidate architectures into an embedding space to form high-performance clusters while maximizing separation from low-performance architectures. This design mitigates the negative influence of poor-quality candidates. To enhance the discriminative power of the PCE, we incorporate a staged sample generation strategy to strengthen the hierarchical representation capacity of the PCE. Additionally, we introduce a training-free simple classifier to efficiently select high-performance architectures from the embedding space. PCNAS achieves high accuracy with low computational cost on NAS-Bench-101 and NAS-Bench- 201, outperforming previous approaches. Furthermore, PCNAS exhibits strong efficiency in the DARTS search space, discovering a high-performing architecture with a 2.53% error rate using only 0.5 GPU days of search cost, and on MobileNetV3 with ImageNet, achieving 78.12% top-1 accuracy using only 0.3 GPU days.
- 11 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive and Developmental Systems
- Vol. PP  (23798920) , 1-15
Surrogate-Assisted Neural Architecture Search with Performance Clustering
Evolutionary neural architecture search (ENAS) automates the design of neural network architectures but incurs significant computational costs during the evaluation phase of candidate neural networks in the evolutionary algorithm. To address this issue, surrogate models are widely adopted to estimate the performance of candidate architectures, thereby reducing resource consumption. However, existing surrogate models are primarily based on regression or classification. They are often hindered by interference from low-quality architectures, which limits search efficiency and final performance. To overcome these challenges, we propose surrogate-assisted neural architecture search with performance clustering (PCNAS). PCNAS introduces a contrastive learning-based performance clustering encoder (PCE). The PCE maps candidate architectures into an embedding space to form high-performance clusters while maximizing separation from low-performance architectures. This design mitigates the negative influence of poor-quality candidates. To enhance the discriminative power of the PCE, we incorporate a staged sample generation strategy to strengthen the hierarchical representation capacity of the PCE. Additionally, we introduce a training-free simple classifier to efficiently select high-performance architectures from the embedding space. PCNAS achieves high accuracy with low computational cost on NAS-Bench-101 and NAS-Bench- 201, outperforming previous approaches. Furthermore, PCNAS exhibits strong efficiency in the DARTS search space, discovering a high-performing architecture with a 2.53% error rate using only 0.5 GPU days of search cost, and on MobileNetV3 with ImageNet, achieving 78.12% top-1 accuracy using only 0.3 GPU days.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 64, 5105317
FBAP-Net: A Frequency-Band-Aware Amplitude–Phase Network for Precipitation Nowcasting
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 64, 5105317
FBAP-Net: A Frequency-Band-Aware Amplitude–Phase Network for Precipitation Nowcasting
- Open Access
- 15 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 167-184
A Sample-Free Compilation Framework for Efficient Dynamic Tensor Computation
- 15 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 167-184
Open AccessA Sample-Free Compilation Framework for Efficient Dynamic Tensor Computation
- 13 August 2025
- Published by Elsevier in Neurocomputing
- Vol. 654
Predictor-assisted evolutionary neural architecture search for spiking neural networks
- 13 August 2025
- Published by Elsevier in Neurocomputing
- Vol. 654
Predictor-assisted evolutionary neural architecture search for spiking neural networks
- Open Access
- 8 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 57-72
Scaling Large-scale GNN Training to Thousands of Processors on CPU-based Supercomputers
- 8 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 57-72
Open AccessScaling Large-scale GNN Training to Thousands of Processors on CPU-based Supercomputers
- 22 May 2025
- Published by Elsevier in Future Generation Computer Systems
- Vol. 173
Noisy data-based attack: A new type of untargeted attack in Federated Learning and its countermeasures
- 22 May 2025
- Published by Elsevier in Future Generation Computer Systems
- Vol. 173
Noisy data-based attack: A new type of untargeted attack in Federated Learning and its countermeasures
- Open Access
- 28 February 2025
- Published by Association for Computing Machinery (ACM)
- p. 566-568
A General and Scalable GCN Training Framework on CPU Supercomputers
Graph Convolutional Networks (GCNs) are widely used in various domains. However, training distributed full-batch GCNs on large-scale graphs poses challenges due to inefficient memory access patterns and high communication overhead. This paper presents a general and efficient GCN training framework on CPU supercomputers. It comprises a general aggregation kernel designed to optimize irregular memory access and a quantization method with label propagation to reduce communication overhead. Experimental results show that our method achieves a speedup of up to 4.1Ă— compared with the SoTA implementations.
- 28 February 2025
- Published by Association for Computing Machinery (ACM)
- p. 566-568
Open AccessA General and Scalable GCN Training Framework on CPU Supercomputers
Graph Convolutional Networks (GCNs) are widely used in various domains. However, training distributed full-batch GCNs on large-scale graphs poses challenges due to inefficient memory access patterns and high communication overhead. This paper presents a general and efficient GCN training framework on CPU supercomputers. It comprises a general aggregation kernel designed to optimize irregular memory access and a quantization method with label propagation to reduce communication overhead. Experimental results show that our method achieves a speedup of up to 4.1Ă— compared with the SoTA implementations.
- Open Access
- 3 February 2025
- Published by Elsevier in Computer Methods and Programs in Biomedicine
- Vol. 261, 108616
Antimicrobial resistance recommendations via electronic health records with graph representation and patient population modeling
- 3 February 2025
- Published by Elsevier in Computer Methods and Programs in Biomedicine
- Vol. 261, 108616
Open AccessAntimicrobial resistance recommendations via electronic health records with graph representation and patient population modeling