基本信息

陈广勇  男    中国科学院深圳先进技术研究院
电子邮件： gy.chen@siat.ac.cn
通信地址： 深圳市南山区学苑大道1068号
邮政编码： 518048

研究领域

机器学习理论及其应用

教育背景

   
学历

  • 2012年，南京大学，电子科学与工程学院，本科

  • 2016年，香港中文大学，计算机科学与工程系，博士

工作经历

  • 2020 至今: 中国科学院深圳先进技术研究院， 副研究员

  • 2018 - 2020: 腾讯量子实验室，高级研究员

  • 2016 - 2018: 香港中文大学，博士后研究员

论文发表

# denotes visiting or intern students supervised by me, * denotes corresponding authors.

  1. Accelerated Prediction of Cu-based Single-Atom Alloy Catalysts for CO2 Reduction by Machine Learning.
    Dashuai Wang, Runfeng Cao, Shaogang Hao, Chen Liang, Guangyong Chen, Pengfei Chen, Yang Lie, Xiaolong Zou
    Green Energy & Environment, JCR Q1, 2021.

  2. Flattening Sharpness for Dynamic Gradient Projection Memory Benefits Continual Learning.
    Danruo Deng, Guangyong Chen*, Jianye Hao, Qiong Wang, Pheng-Ann Heng.
    2021 Conference on Neural Information Processing Systems (NeurIPS), CCF A, 2021. 

  3. Learning Regularizer for Monocular Depth Estimation with Adversarial Guidance.
    Guibao Shen#, Yingkui Zhang, jialu Li, Mingqiang Wei, Qiong Wang*, Guangyong Chen*, Pheng-Ann Heng.
    The 29th ACM International Conference on Multimedia (ACMMM), CCF A, 2021.

  4. A Rotation-invariant Framework for Deep Point Cloud Analysis.
    Xianzhi Li, Ruihui Li, Guangyong Chen, Chi-Wing Fu, Daniel Cohen-Or, Pheng-Ann Heng.
    IEEE Transactions on Visualization and Computer Graphics (TVCG), JCR Q1, 2021.

  5. RetroPrime:  A Diverse, plausible and Transformer-based method for Single-Step retrosynthesis predictions.
    Xiaorui Wang, Yuquan Li, Jiezhong Qiu, Guangyong Chen, Huanxiang Liu, Benben Liao, Chang-Yu Hsieh, Xiaojun Yao
    Chemical Engineering Journal, JCR Q1, 2021.

  6. Hyperbolic Relational Graph Convolution Networks Plus: a Simple but Highly Efficient QSAR-modeling Method.
    Zhenxing Wu, Dejun Jiang, Chang-Yu Hsieh, Guangyong Chen, Ben Liao, Dongsheng Cao, Tingjun Hou
    Briefings in Bioinformatics, JCR Q1, 2021.

  7. Could graph neural networks learn better molecular representation for drug discovery? A comparison study of descriptor-based and graph-based models.
    Dejun Jiang, Zhenxing Wu, Chang-Yu Hsieh, Guangyong Chen, Ben Liao, Zhe Wang, Chao Shen, Dongsheng Cao, Jian Wu & Tingjun Hou*
    Journal of Cheminformatics, JCR Q1, 2021.

  8. Noise against noise: stochastic label noise helps combat inherent label noise.
    Pengfei Chen#, Guangyong Chen*, Junjie Ye*, Jingwei Zhao, Pheng Ann Heng.
    Ninth International Conference on Learning Representations (ICLR, Top Conference @ AI), Spotlight, 2021.

  9. Beyond Class-Conditional Assumption: A Primary Attempt to Combat Instance-Dependent Label Noise.
    Pengfei Chen#, Junjie Ye*, Guangyong Chen*, Jingwei Zhao, Pheng Ann Heng.
    Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI, CCF A), 2021.

  10. Robustness of Accuracy Metric and its Inspiration in Learning with Noisy Labels.
    Pengfei Chen#, Junjie Ye*, Guangyong Chen*, Jingwei Zhao, Pheng Ann Heng.
    Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI, CCF A), 2021.

  11. Foresee then Evaluate: Decomposing Value Estimation with Latent Future Prediction.
    Hongyao Tang#, Zhaopeng Meng, Guangyong Chen, Pengfei Chen, Chen Chen, Yaodong Yang, Luo Zhang, Wulong Liu, Jianye Hao
    Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI, CCF A), 2021.

  12. Q-value Path Decomposition for Deep Multiagent Reinforcement Learning.
    Yaodong Yang#, Jianye Hao, Guangyong Chen*, Hongyao Tang, Yingfeng Chen, Yujing Hu, Changjie Fan, Zhongyu Wei.
    Thirty-seventh International Conference on Machine Learning (ICML, CCF A), 2020.

  13. Balancing Between Accuracy and Fairness for Interactive Recommendation with Reinforcement Learning.
    Weiwen Liu#, Feng Liu, Ruiming Tang*, Ben Liao, Guangyong Chen*, Pheng Ann Heng.
    Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), 2020.

  14. PMD: An Optimal Transportation-Based User Distance for Recommender Systems.
    Yitong Meng#, Xinyan Dai, Xiao Yan, James Cheng, Weiwen Liu, Jun Guo, Benben Liao, Guangyong Chen.
    European Conference on Information Retrieval (ECIR), 2020.

  15. Understanding and Utilizing Deep Neural Networks Trained with Noisy Labels.
    Pengfei Chen#, Benben Liao, Guangyong Chen*, Shengyu Zhang.
    Thirty-sixth International Conference on Machine Learning (ICML, CCF A), 2019.

  16. Alchemy: A Quantum Chemistry Dataset for Benchmarking AI Models.
    Guangyong Chen, Pengfei Chen, Chang-Yu Hsieh, Chee-Kong Lee, Benben Liao, Renjie Liao, Weiwen Liu, Jiezhong Qiu, Qiming Sun, Jie Tang, Richard Zemel, Shengyu Zhang.
    Representation Learning on Graphs and Manifolds, ICLR 2019 workshop.(Alchemy Contest)

  17. Psrec: Social Recommendation with Pseudo Ratings.
    Yitong Meng, Guangyong Chen, Jiajin Li, Shengyu Zhang.
    Proceedings of the 12th ACM Conference on Recommender Systems (RecSys), 2018.

  18. Large-Scale Bayesian Probabilistic Matrix Factorization with Memo-Free Distributed Variational Inference.
    Guangyong Chen, Fengyuan Zhu, Pheng Ann Heng.
    ACM Transactions on Knowledge Discovery from Data (TKDD, JCR Q1) 12.3 (2018): 1-24.

  19. Efficient and Robust Emergence of Norms through Heuristic Collective Learning.
    Jianye Hao, Jun Sun Sun, Guangyong Chen, Zan Wang, Chao Yu, Zhong Ming.
    ACM Transactions on Autonomous and Adaptive Systems (TAAS, CCF B) 12.4 (2017): 1-20.

  20. Learning to Aggregate Ordinal Labels by Maximizing Separating Width.
    Guangyong Chen, Shengyu Zhang, Di Lin, Hui Huang, Pheng Ann Heng.
    Thirty-fourth International Conference on Machine Learning (ICML, CCF A) , 2017.

  21. Cascaded Feature Network for Semantic Segmentation of RGB-D Images.
    Di Lin, Guangyong Chen, Daniel Cohen-Or, Pheng-Ann Heng, Hui Huang.
    In Proceedings of the IEEE International Conference on Computer Vision (ICCV, CCF A), 2017.

  22. A Bayesian Nonparametric Approach to Dynamic Dyadic Data Prediction.
    Fengyuan Zhu, Guangyong Chen, Pheng-Ann Heng.
    IEEE 16th International Conference on Data Mining (ICDM, CCF B), 2016

  23. Blind Image Denoising via Dependent Dirichlet Process Tree.
    Fengyuan Zhu, Guangyong Chen *, Jianye Hao, Pheng-Ann Heng.
    IEEE transactions on pattern analysis and machine intelligence (TPAMI, CCF A), 39.8, (2016): 1518-1531.

  24. From Noise Modeling to Blind Image Denoising.
    Fengyuan Zhu, Guangyong Chen, Pheng-Ann Heng.
    In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR, CCF A), 2016.

  25. An Efficient Statistical Method for Image Noise Level Estimation.
    Guangyong Chen, Fengyuan Zhu, Pheng Ann Heng.
    In Proceedings of the IEEE International Conference on Computer Vision (ICCV, CCF A), 2015.


发表论文
[1] Kexin Chen, Guangyong Chen, Junyou Li, Yuansheng Huang, Ercheng Wang, Tingjun Hou, Pheng-Ann Heng. MetaRF: attention-based random forest for reaction yield prediction with a few trails. JOURNAL OF CHEMINFORMATICS[J]. 2023, 15(1): 1-12, http://dx.doi.org/10.1186/s13321-023-00715-x.
[2] 邓丹若, 陈广勇, 余洋, 刘扶芮, 王平安. Uncertainty Estimation by Fisher Information-based Evidential Deep Learning. ICMLnull. 2023, [3] Zhou, Donghao, Chen, Pengfei, Wang, Qiong, Chen, Guangyong, Heng, PhengAnn. Acknowledging the Unknown for Multi-label Learning with Single Positive Labels. ECCVnull. 2022, [4] 周芯怡, 叶俊杰, Chak Wa Pui, Kun Shao, Guangliang Zhang, Bin Wang, 郝建业, 陈广勇, 王平安. Heterogeneous Graph Neural Network-based Imitation Learning for Gate Sizing Acceleration. ICCADnull. 2022, [5] Wang, Bowen, Shen, Guibao, Li, Dong, Hao, Jianye, Liu, Wulong, Huang, Yu, Wu, Hongzhong, Lin, Yibo, Chen, Guangyong, Heng, Pheng Ann. LHNN: Lattice Hypergraph Neural Network for VLSI Congestion Prediction. DACnull. 2022, [6] Yaodong Yang, 陈广勇, Weixun Wang, Xiaotian Hao, 郝建业, 王平安. Transformer-based working memory for multiagent reinforcement learning with action parsing. Advances in Neural Information Processing Systemsnull. 2022, [7] 李金鹏, 陈广勇, 毛航宇, 邓丹若, 李栋, 郝建业, 窦琪, 王平安. Flat-Aware Cross-Stage Distilled Framework for Imbalanced Medical Image Classification. MICCAInull. 2022, [8] Zhongwei Wan, 陈广勇. G-MAP: General Memory-Augmented Pre-trained Language Model for Domain Tasks. 60th Annual Meeting of the Association for Computational Linguisticsnull. 2022, [9] Chen Guangyong. Robustness of Accuracy Metric and its Inspiration in Learning with Noisy Labels. Thirty-Fifth AAAI Conference on Artificial Intelligence. 2021, [10] 陈鹏飞, Chen Guangyong, 叶俊杰, jingwei zhao, 王平安. Noise against noise: stochastic label noise helps combat inherent label noise.. Ninth International Conference on Learning Representationsnull. 2021, [11] Wu, Zhenxing, Jiang, Dejun, Hsieh, ChangYu, Chen, Guangyong, Liao, Ben, Cao, Dongsheng, Hou, Tingjun. Hyperbolic relational graph convolution networks plus: a simple but highly efficient QSAR-modeling method. BRIEFINGS IN BIOINFORMATICS[J]. 2021, 22(5): http://dx.doi.org/10.1093/bib/bbab112.
[12] Jiang, Dejun, Wu, Zhenxing, Hsieh, ChangYu, Chen, Guangyong, Liao, Ben, Wang, Zhe, Shen, Chao, Cao, Dongsheng, Wu, Jian, Hou, Tingjun. Could graph neural networks learn better molecular representation for drug discovery? A comparison study of descriptor-based and graph-based models. JOURNAL OF CHEMINFORMATICS[J]. 2021, 13(1): https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7888189/.
[13] Tang, Hongyao, Hao, Jianye, Chen, Guangyong, Chen, Pengfei, Chen, Chen, Yang, Yaodong, Zhang, Luo, Liu, Wulong, Meng, Zhaopeng. Foresee then Evaluate: Decomposing Value Estimation with Latent Future Prediction. 2021, http://arxiv.org/abs/2103.02225.
[14] Chen, Pengfei, Ye, Junjie, Chen, Guangyong, Zhao, Jingwei, Heng, PhengAnn. Beyond Class-Conditional Assumption: A Primary Attempt to Combat Instance-Dependent Label Noise. AAAInull. 2020, http://arxiv.org/abs/2012.05458.
[15] 陈广勇. 面向深度多智能强化学习系统的Q值路径分解算法. Proceedings of the 37th International Conference on Machine Learning. 2020, [16] 陈广勇. 基于强化学习算法平衡推荐系统的精度与公平. Pacific-Asia Conference on Knowledge Discovery and Data Mining. 2020, [17] 陈广勇. 理解和运用基于噪声标签训练的深度神经网络. Proceedings of the 36th International Conference on Machine Learning. 2019, [18] 陈广勇. 基于无需缓存的分布式变分推理的大尺度贝叶斯概率矩阵分解算法. ACM Transactions on Knowledge Discovery from Data. 2018, [19] 陈广勇. 基于伪标签的社交推荐. Proceedings of the 12th ACM Conference on Recommender Systems. 2018, [20] 陈广勇. 面向RGB-D图像语义分割的瀑布特征网络. Proceedings of the IEEE International Conference on Computer Vision. 2017, [21] 陈广勇. 基于最大化边际距离的有序标签综合算法. Proceedings of the 34th International Conference on Machine Learning. 2017, [22] 陈广勇. 从噪声建模到盲源图像去噪. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016, [23] 陈广勇. 一种面向动态二元数据估计的贝叶斯非参方法. Proceedings of the 16th IEEE International Conference on Data Mining. 2016, [24] 陈广勇. 基于互相依赖的Dirichlet过程树的盲源图像去噪算法. IEEE transactions on pattern analysis and machine intelligence. 2016, [25] 陈广勇. 一种高效的图像噪声估计的统计学算法. In Proceedings of the IEEE International Conference on Computer Vision. 2015,