Hongbin Pei (裴红斌)

Hongbin Pei (裴红斌)

Assistant Professor

Hey, my name is Hongbin Pei (裴红斌), an assistant professor at School of Cyber Science and Engineering, Xi’an Jiaotong University (西安交通大学). I received B.Sc, M.Eng, and Ph.D. degree from the College of Computer Science and Technology, Jilin University (吉林大学). My research interest focuses on Machine Learning and Complex Networks. I published several papers at the top international AI conferences and journals, such as IEEE TPAMI, ICLR, NeurIPS.

个人主页（中文） https://gr.xjtu.edu.cn/en/web/peihongbin

🔥 News

  • 2024.06:  🎉🎉 We got one paper accepted for Spotlight Presentation at ICML’24 (CCF-A)
  • 2024.02:  🎉🎉 I was awarded the Excellent Doctoral Dissertation nomination Award for the Wu Wenjun Science and Technology Award (吴文俊科学技术奖优秀博士论文提名奖) Link
  • 2024.02:  🎉🎉 We got one paper accepted by IEEE TPAMI (CCF-A)
  • 2024.01:  🎉🎉 We got one paper accepted for presentation at WWW’24 (CCF-A)
  • 2023.12:  🎉🎉 I was nominated by the program chair committee of ICML 2024 to serve as Reviewer
  • 2023.12:  🎉🎉 We got two papers accepted for presentation at AAAI’24 (CCF-A)
  • 2023.12:  🎉🎉 I participated in and delivered a talk at the Xiangshan Science Conference (香山科学会议)
  • 2022.08:  🎉🎉 Our “On the Dimension and Metric of Network Embedding” (网络嵌入的维数与度量研究) project is selected to be awarded by NSFC (中国国家自然科学基金)

📝 Selected Publications

ICLR 2020
sym

Geom-GCN: Geometric Graph Convolutional Networks Code

Hongbin Pei, Bingzhe Wei, Kevin Chen-Chuan Chang, Yu Lei, Bo Yang. The International Conference on Learning Representations (ICLR), 2020

Key contribution: We point out two fundamental weaknesses of message-passing neural network, i.e.., losing the structural information of nodes in neighborhoods and lacking the ability to capture long-range dependencies in disassortative graphs.

The paper is the first work to raise the problem of graph learning heterophily, and gains more than google scholar citations 750+.

IEEE TPAMI
sym

Active Surveillance via Group Sparse Bayesian Learning Code

Hongbin Pei, Bo Yang, Jiming Liu, Kevin Chen-Chuan Chang. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022

Key contribution: We formulate the active surveillance task as a row sparse sentinel network mining problem for the first time. We apply the proposed active surveillance algorithm into malaria surveillance in border areas of China and Myanmar, which played a crucial role in the elimination of malaria in Yunnan.

We investigated malaria cases many times in border areas of China and Myanmar; a snapshot is shown on the left.

Slected Publications

[2024] Hongbin Pei, Yu Li, Huiqi Deng, Jingxin Hai, Pinghui Wang, Jie Ma, Jing Tao, Yuheng Xiong, Xiaohong Guan. Multi-Track Message Passing: Tackling Oversmoothing and Oversquashing in Graph Learning via Preventing Heterophily Mixing. The forty-first International Conference on Machine Learning (ICML), 2024（（CCF-A）；Spotlight representation））

[2024] Hongbin Pei, Yuheng Xiong, Pinghui Wang, Jing Tao, Jialun Liu, Huiqi Deng, Jie Ma, Xiaohong Guan. Memory Disagreement: A Pseudo-Labeling Measure from Training Dynamics for Semi-supervised Graph Learning. The 2024 ACM Web Conference (WWW), 2024 （CCF-A）

[2024] Hongbin Pei, Taile Chen, Chen A, Huiqi Deng, Jing Tao, Pinghui Wang, Xiaohong Guan. HAGO-Net: Hierarchical Geometric Massage Passing for Molecular Representation Learning. Thirty-eighth AAAI Conference on Artificial Intelligence (AAAI), 2024 （CCF-A）

[2024] Jie Ma, Pinghui Wang, Dechen Kong, Zewei Wang, Jun Liu, Hongbin Pei, Junzhou Zhao. Robust Visual Question Answering: Datasets, Methods, and Future Challenges. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024 (CCF-A; impact factor 24.31)

[2024] Jinjin Chi, Zhichao Zhang, Zhiyao Yang, Jihong Ouyang, Hongbin Pei (Corresponding Author). Generalized Variational Inference via Optimal Transport. Thirty-eighth AAAI Conference on Artificial Intelligence (AAAI), 2024 （CCF-A）

[2023] Chunxu Zhang, Ximing Li, Hongbin Pei, Zijian Zhang, Bing Liu, Bo Yang. LaenNet: Learning robust GCNs by propagating labels. Neural Networks, 2023 （CCF-B）

[2022] Hongbin Pei, Bo Yang, Jiming Liu, Kevin Chen-Chuan Chang. Active Surveillance via Group Sparse Bayesian Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022 （CCF-A; impact factor 24.31; ESI Hot Paper (top 0.1%)）

[2022] 王平辉, 裴红斌, 赵俊舟, 秦涛, 沈超, 刘东亮, 管晓宏. 网络社会现代治理的挑战与对策. 中国科学院院刊, 2022

[2022] Jialun Liu, Yifan Sun, Feng Zhu, Hongbin Pei, Yi Yang, Wenhui Li. Learning Memory-Augmented Unidirectional Metrics for Cross-Modality Person Re-Identification. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022 （CCF-A）

[2022] Jialun Liu, Yifan Sun, Yijin Xu, Hongbin Pei, Wenhui Li. Feature Cloud: Improving Deep Visual Recognition With Probabilistic Feature Augmentation. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2022 （CCF-B）

[2020] Hongbin Pei, Bingzhe Wei, Kevin Chen-Chuan Chang, Yu Lei, Bo Yang. Geom-GCN: Geometric Graph Convolutional Networks. The eighth International Conference on Learning Representations (ICLR), 2020 （Tsinghua University CS-A; Spotlight Presentation, google scholar citations 750+）

[2020] Hongbin Pei, Bingzhe Wei, Kevin Chen-Chuan Chang, Chunxu Zhang, Bo Yang. Curvature Regularization to Prevent Distortion in Graph Embedding. Thirty-fourth Conference on Neural Information Processing Systems (NeurIPS), 2020 （CCF-A; Spotlight Presentation）

[2020] Yu Lei, Zhitao Wang, Wenjie Li, Hongbin Pei, Quanyu Dai. Social Attentive Deep Q-networks for Recommender Systems. IEEE Transactions on Knowledge and Data Engineering (TKDE), 2020 （CCF-A）

[2020] Yu Lei, Hongbin Pei, Hanqi Yan, Wenjie Li. Reinforcement learning based recommendation with graph convolutional q-network. 43rd international ACM SIGIR conference on research and development in information retrieval (SIGIR), 2020 （CCF-A）

[2019] Yu Lei, Zhitao Wang, Wenjie Li, Hongbin Pei. Social attentive deep q-network for recommendation. 42nd international ACM SIGIR conference on research and development in information retrieval (SIGIR), 2019 （CCF-A）

[2018] Hongbin Pei, Bo Yang, Jiming Liu, Lei Dong. Group Sparse Bayesian Learning for Actively Surveillance on Epidemic Dynamics. Thirty-second AAAI Conference on Artificial Intelligence (AAAI), 2018 （CCF-A; Spotlight Presentation）

[2017] Bo Yang, Hongbin Pei, Hechang Chen, Jiming Liu, Shang Xia. Characterizing and Discovering Spatiotemporal Social Contact Patterns for Healthcare. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2017 （CCF-A; impact factor 24.31）

[2017] Jingbo Zhou, Hongbin Pei, Haishan Wu. Early Warning of Human Crowds Based on Query Data from Baidu Map: Analysis Based on Shanghai Stampede. arXiv:1603.06780, 2017 （This paper attract widespread attention and is reported by many international media, including MIT Technology Review (麻省理工科技评论), Wall Street Journal (华尔街日报), South China Morning Post (南华早报) ）

译著

《机器学习精讲：基础、算法及应用》杰瑞米·瓦特、雷萨·博哈尼、阿格洛斯·K.卡萨格罗斯. 机械工业出版社. ISBN 9787111611967. 2019 （负责第五章和第六章）

🚀 Research Projects

  • 国家自然科学基金（青年项目），“网络嵌入的维数与度量研究”，62202369，2023-2025

  • 博士后创新人才支持计划（博新计划），“大规模动态异质网络表示学习方法与应用”，BX2021240，2021-2023 (全国400人入选，其中计算机学科仅14人)

  • 北京交通发展研究院——揭榜挂帅课题，“基于街景、遥感图像等多源数据的城市用地规模与功能预测及在交通网络的应用”，2022-2023

  • 智能网络与网络安全教育部重点实验室——青年学术骨干培植项目，“大规模图解耦表示学习方法及应用”，2022-2023

  • 符号计算与知识工程教育部重点实验室——开放课题，“面向3D分子表示学习的层次几何图神经网络”，2022-2024

🎖 Honors

  • 吴文俊人工智能优秀博士论文提名奖, 2024

  • 吉林大学优秀博士学位论文，2022

  • 吉林省自然科学奖一等奖，2021

  • 全国博士后创新创业大赛优胜奖，2021

🎓 Educations

  • 2015.09 - 2021.06, Ph.D in Computer Science and Technology, Jilin University

  • 2012.09 - 2015.06, M.Eng in Computer Science and Technology, Jilin University

  • 2008.09 - 2012.06, B.Sc in Computer Science and Technology, Jilin University

🚢 Visiting Experience

2019.01 - 2020.12, Visiting Scholar, Data and Information Systems Laboratory (DAIS), University of Illinois at Urbana-Champaign (UIUC)

2016.06 - 2017.06, Research Assistant, Centre for Health Informatics (HIC), Hong Kong Baptist Univeristy (HKBU)

🔉 Invited Talks

  • 2023.12, 网络社会治理关键信息技术清单, 信息技术支撑国家治理现代化的战略研究, 香山科学会议 (我国科技界以探索科学前沿、促进知识创新为主要目标的高层次、跨学科、小规模常设性学术会议), 北京香山饭店, 北京

  • 2023.11, 嵌入物理空间的坐标图学习：从分子到城市, 2023年”智能计算”博士后学术交流活动, 之江实验室, 杭州

  • 2022.05, 网络几何, 生物神经智能—神经网络与图神经网络研讨会, 中国人工智能学会CAAI, 在线

  • 2021.06, 数据驱动的复杂网络分析理论与方法, 第四届全国”博新计划”前沿论坛, 北京科学会堂, 北京

  • 2018.05, 接触跟踪：下一代的传染病防控技术, 西南大学, 重庆

  • 2017.08, 人类接触时空模式的建模与推断, 博士生论坛, 中国计算机学会CCF, 昆明

  • 2016.11, 面向边境疟疾控制的主动监控系统, 中国疾病预防控制中心寄生虫病预防控制所, 上海

💻 Pubilic Services

  • 顶会审稿人: ICML, ICLR, NeurIPS, AAAI, IJCAI, CVPR, ICCV, KDD, SDM
  • 顶刊审稿人: IEEE TPAMI, IEEE TKDE, IEEE TNNLS

📙 Books that inspired me most

  • 《超越时空——通过平行宇宙、时间卷曲和第十维度的科学之旅》 by 加来道雄
  • 《哲学之树》 by Stephen R. Palmquist
  • 《Probably Approximately Correct: Nature’s Algorithms for Learning and Prospering in a Complex World》 by Leslie Valiant
  • 《背水一战：从纱厂小工到大学校长》 by 孔宪铎

The beautiful tree of life on earth

We are merely a leaf of the tree; enjoy life! The ability to Create Knowledge may be the key to differentiating us from other leaves.

WechatIMG684

The figure was created by Evogeneao.