🤵🏻 About Me
I am an Associate Researcher at the School of Software Engineering/Suzhou Institute for Advanced Research, University of Science and Technology of China (USTC), and a member of the USTC-DILab. I received my Ph.D. in the School of Data Science, University of Science and Technology of China (USTC), supervised by associate professor Yang Wang (汪炀) and professor Qi Liu (刘淇)). Before starting my Ph.D. study, I received my Bachelor's degree from Jilin University (JLU) in 2017. I have published more than 30 high-level papers on research journals and conferences, including some top level international journals and conferences, such as ICML, NeurIPS, ICLR, and some IEEE Transactions, such as IEEE TKDE and IEEE TMC. I am broadly interested in open environment data mining and generalized AI for science.
Most recently, I am interested in the following topics:
- Open Environment Data Mining and Model Generalization
- Non-ideal Data Distribution: Imbalanced/Long-tailed Learning and Out-of-Distribution (OOD) Generalization
- Dynamic Data Distribution: Continual Learning
- Sparse Data Distribution: Interpretable Data Augmentation
- Variable Learning Objective: Multi-objective Optimization
- Generalized AI for Science
- AI for City and Transportation: Spatiotemporal Data Mining
- AI for Chemistry: Spectrum-Structure-Property Relationship Learning (e.g., PXRD, NMR)
- AI for EDA: Intelligent Electronic Design Automation
📢: 招收对深度学习、AI4Science感兴趣且有较好数理基础的学生 [推免/工程实践/远程科研实习],可通过邮箱联系我,请附上个人简历。
📢: 中国科学技术大学数据智能实验室(DILab)诚招特任副研究员及博士后! 研究方向包括时空数据挖掘、开放机器学习与模型泛化、AI for Science。如您对团队研究方向感兴趣,欢迎您直接与团队负责人汪炀老师联系!
🎉 News
📝 Publications
( *, Corresponding author +, Equal contribution )Preprints
- Delayed Bottlenecking: Alleviating Forgetting in Pre-trained Graph Neural Networks
Zhe Zhao, Pengkun Wang*, Xu Wang, Haibin Wen, Xiaolong Xie, Qingfu Zhang, Yang Wang*
Submitted to IEEE TKDE [PDF]
- RayE-Sub: Countering Subgraph Degradation via Perfect Reconstruction
Kuo Yang, Zhengyang Zhou*, Xu Wang, Pengkun Wang, Limin Li, Yang Wang*
Submitted to IEEE TKDE [PDF]
- Graph-Free Learning in Graph-Structured Data: A More Efficient and Accurate Spatiotemporal Learning Perspective
Xu Wang, Pengfei Gu, Pengkun Wang, Binwu Wang, Zhengyang Zhou, Lei Bai*, Yang Wang*
arXiv preprint [PDF]
Conference Papers
- Breaking Long-Tailed Learning Bottlenecks: A Controllable Paradigm with Hypernetwork-Generated Diverse Experts
Zhe Zhao, Haibin Wen, Zikang Wang, Pengkun Wang*, Fanfu Wang, Song Lai, Qingfu Zhang, Yang Wang*
NeurIPS 2024 (Annual Conference on Neural Information Processing Systems, CCF-A, (Spotlight)) - LLM-AutoDA: Large Language Model-Driven Automatic Data Augmentation for Long-tailed Problems
Pengkun Wang+, Zhe Zhao+, Haibin Wen, Fanfu Wang, Binwu Wang, Qingfu Zhang*, Yang Wang*
NeurIPS 2024 (Annual Conference on Neural Information Processing Systems, CCF-A) - XRDMamba: Large-scale Crystal Material Space Group Identification with Selective State Space Model
Liheng Yu, Pengkun Wang*, Zhe Zhao, Zhongchao Yi, Sun Nan, Di Wu, Yang Wang*
CIKM 2024 (ACM International Conference on Information and Knowledge Management, CCF-B) - STONE: A Spatio-temporal OOD Learning Framework Kills Both Spatial and Temporal Shifts
Binwu Wang, Jiaming Ma*, Pengkun Wang, Xu Wang, Yudong Zhang, Zhengyang Zhou, Yang Wang*
KDD 2024 (ACM SIGKDD Conference on Knowledge Discovery and Data Mining, CCF-A) [PDF]
- Two Fists, One Heart: Multi-Objective Optimization Based Strategy Fusion for Long-tailed Learning
Zhe Zhao, Pengkun Wang*, HaiBin Wen, Wei Xu, Lai Song, Qingfu Zhang, Yang Wang*
ICML 2024 (International Conference on Machine Learning, CCF-A) [PDF]
- Make Bricks With A Little Straw: Large-Scale Spatio-temporal Graph Learning with Restricted GPU-Memory Capacity
Binwu Wang, Pengkun Wang*, Zhengyang Zhou, Zhe Zhao, Wei Xu, Yang Wang*
IJCAI 2024 (International Joint Conference on Artificial Intelligence, CCF-A) [PDF]
- When Imbalance Meets Imbalance: Structure-driven Learning for Imbalanced Graph Classification
Wei Xu, Pengkun Wang*, Zhe Zhao, Binwu Wang, Xu Wang, Yang Wang*
WWW 2024 (The Web Conference, CCF-A) [PDF]
- Kill Two Birds with One Stone: Rethinking Data Augmentation for Deep Long-tailed Learning
Binwu Wang, Pengkun Wang*, Wei Xu, Xu Wang, Yudong Zhang, Kun Wang, Yang Wang*
ICLR 2024 (International Conference on Learning Representations, 清华-A) [PDF]
- A Twist for Graph Classification: Optimizing Causal Information Flow in Graph Neural Networks
Zhe Zhao, Pengkun Wang*, HaiBin Wen, Yudong Zhang, Zhengyang Zhou, Yang Wang*
AAAI 2024 (AAAI Conference on Artificial Intelligence, CCF-A) [PDF]
- Towards Dynamic Spatial-Temporal Graph Learning: A Decoupled Perspective
Binwu Wang, Pengkun Wang*, Yudong Zhang, Xu Wang, Zhengyang Zhou, Lei Bai, Yang Wang*
AAAI 2024 (AAAI Conference on Artificial Intelligence, CCF-A) [PDF]
- Graph Networks Stand Strong: Enhancing Robustness via Stability Constraints
Zhe Zhao, Pengkun Wang*, Haibin Wen, Yudong Zhang, Binwu Wang, Yang Wang*
ICASSP 2024 (IEEE International Conference on Acoustics, Speech and Signal Processing, CCF-B) [PDF]
- Gradient Reactivation Enhanced Causal Attention for Out-Of-Distribution Generalizable Graph Classification
Xu Wang, Pengfei Gu, Yudong Zhang, Binwu Wang, Pengkun Wang, Yang Wang*
ICASSP 2024 (IEEE International Conference on Acoustics, Speech and Signal Processing, CCF-B) [PDF]
- Face Anti-spoofing with Unknown Attacks: A Comprehensive Feature Extraction and Representation Perspective
Xu Wang, Pengkun Wang, Yudong Zhang, Binwu Wang
CVM 2024 (International Conference on Computational Visual Media, CCF-C) - An Observed Value Consistent Diffusion Model for Imputing Missing Values in Multivariate Time Series
Xu Wang, Hongbo Zhang, Pengkun Wang, Yudong Zhang, Binwu Wang, Zhengyang Zhou, Yang Wang*
KDD 2023 (ACM SIGKDD Conference on Knowledge Discovery and Data Mining, CCF-A) [PDF]
- Pattern Expansion and Consolidation on Evolving Graphs for Continual Traffic Prediction
Binwu Wang, Yudong Zhang, Xu Wang, Pengkun Wang, Zhengyang Zhou, Lei Bai, Yang Wang*
KDD 2023 (ACM SIGKDD Conference on Knowledge Discovery and Data Mining, CCF-A) [PDF]
- EXTRACT and REFINE: Finding A Support Subgraph Set for Graph Representation
Kuo Yang, Zhengyang Zhou, Wei Sun, Pengkun Wang, Xu Wang, Yang Wang*
KDD 2023 (ACM SIGKDD Conference on Knowledge Discovery and Data Mining, CCF-A) [PDF]
- Pondering about Task Spatial Misalignment: Classification-Localization Equilibrated Object Detection
Yudong Zhang, Wei Lu, Xu Wang, Pengkun Wang*, Yang Wang*
ICASSP 2023 (IEEE International Conference on Acoustics, Speech and Signal Processing, CCF-B) [PDF]
- Searching Lottery Tickets in Graph Neural Networks: A Dual Perspective
Kun Wang, Yuxuan Liang, Pengkun Wang, Xu Wang, Pengfei Gu, Junfeng Fang, Yang Wang*
ICLR 2023 (International Conference on Learning Representations, 清华-A) [PDF]
- Long-tailed Time Series Classification via Feature Space Rebalancing
Pengkun Wang, Xu Wang, Binwu Wang, Yudong Zhang, Lei Bai*, Yang Wang*
DASFAA 2023 (International Conference on Database Systems for Advanced Applications, CCF-B) [PDF] [SLIDE]
- A Knowledge-Driven Memory System for Traffic Flow Prediction
Binwu Wang, Yudong Zhang, Pengkun Wang, Xu Wang, Lei Bai*, Yang Wang*
DASFAA 2023 (International Conference on Database Systems for Advanced Applications, CCF-B) [PDF]
- A Multi-graph Fusion Based Spatiotemporal Dynamic Learning Framework
Xu Wang, Lianliang Chen, Hongbo Zhang, Pengkun Wang, Zhengyang Zhou, Yang Wang*
WSDM 2023 (ACM International Conference on Web Search and Data Mining, CCF-B) [PDF]
- Countering Modal Redundancy and Heterogeneity: A Self-Correcting Multimodal Fusion
Pengkun Wang, Xu Wang, Binwu Wang, Yudong Zhang, Lei Bai*, Yang Wang*
ICDM 2022 (IEEE International Conference on Data Mining, CCF-B) [PDF] [SLIDE]
- Data-driven Vehicular Communications in Urban Vehicular Network
Wen Zhang, Zhengyang Zhou, Chuancai Ge, Pengkun Wang
ICCSN 2019 (International Conference on Communication Software and Networks) [PDF]
- Stack ResNet For Short-term Accident Risk Prediction Leveraging Cross-domain Data
Zhengyang Zhou, Lianliang Chen, Chaochao Zhu, Pengkun Wang
CAC 2019 (China Automation Congress) [PDF]
Journal Papers
- Meta Koopman Decomposition for Time Series Forecasting Under Temporal Distribution Shifts
Yudong Zhang, Xu Wang*, Zhaoyang Sun, Pengkun Wang, Binwu Wang, Limin Li, Yang Wang*
AEI, In Press (Advanced Engineering Informatics, JCR-Q1/Top, IF=8) [PDF]
- Modeling Spatio-Temporal Mobility across Data Silos via Personalized Federated Learning
Yudong Zhang , Xu Wang*, Pengkun Wang, Binwu Wang, Zhengyang Zhou, Yang Wang*
IEEE TMC, In Press (IEEE Transactions on Mobile Computing, CCF-A/JCR-Q1/Top, IF=7.7) - Face Anti-spoofing with Unknown Attacks: A Comprehensive Feature Extraction and Representation Perspective
Li liming, Binwu Wang*, Xu Wang, Pengkun Wang, Yudong Zhang, Yang Wang*
JCST 2024, In Press (Journal of Computer Science and Technology, CCF-B) - Adaptive and Interactive Multi-level Spatio-Temporal Network for Traffic Forecasting
Yudong Zhang, Pengkun Wang, Binwu Wang, Xu Wang, Zhe Zhao, Zhengyang Zhou, Lei Bai*, Yang Wang*
IEEE TITS 2024, In Press (IEEE Transactions on Intelligent Transportation Systems, CCF-B/JCR-Q1/Top, IF=8.5) - Condition-Guided Urban Traffic Co-Prediction With Multiple Sparse Surveillance Data
Binwu Wang, Pengkun Wang*, Yudong Zhang, Xu Wang, Zhengyang Zhou, Yang Wang*
IEEE TVT 2024, In Press (IEEE Transactions on Vehicular Technology, JCR-Q1/Top, IF=6.8) [PDF]
- Latent Gaussian Processes based Graph Learning for Urban Traffic Prediction
Xu Wang, Pengkun Wang, Binwu Wang, Yudong Zhang, Zhengyang Zhou, Lei Bai, Yang Wang*
IEEE TVT 2024, 73(1): 282-294 (IEEE Transactions on Vehicular Technology, JCR-Q1/Top, IF=6.8) [PDF]
- Knowledge Expansion and Consolidation for Continual Traffic Prediction with Expanding Graphs
Binwu Wang, Yudong Zhang, Jiahao Shi, Pengkun Wang, Xu Wang, Lei Bai*, Yang Wang*
IEEE TITS 2023, 24(7): 7190-7201 (IEEE Transactions on Intelligent Transportation Systems, CCF-B/JCR-Q1/Top, IF=8.5) [PDF]
- Joint Gated Co-attention Based Multi-modal Networks for Subregion House Price Prediction
Pengkun Wang, Chuancai Ge, Zhengyang Zhou, Xu Wang, Yuantao Li, Yang Wang*
IEEE TKDE 2023, 35(02): 1667-1680 (IEEE Transactions on Knowledge and Data Engineering, CCF-A/JCR-Q1, IF=8.9) [PDF]
- 基于教师-学生时空半监督网络的城市事件预测方法
周正阳, 刘浩, 王琨, 王鹏焜, 王旭, 汪炀*
电子学报 2023, 51(12): 3557-3571 (CCF-A 中文) [PDF]
- A2DJP: A Two Graph-based Component Fused Learning Framework for Urban Anomaly Distribution and Duration Joint-Prediction
Kun Wang, Zhengyang Zhou, Xu Wang, Pengkun Wang, Qi Fang, Yang Wang*
IEEE TKDE 2023, 35(12): 11984-11998 (IEEE Transactions on Knowledge and Data Engineering, CCF-A/JCR-Q1, IF=8.9) [PDF]
- Inferring Intersection Traffic Patterns with Sparse Video Surveillance Information: An ST-GAN method
Pengkun Wang, Chaochao Zhu, Xu Wang, Zhengyang Zhou, Guang Wang, Yang Wang*
IEEE TVT 2022, 71(9): 9840-9852 (IEEE Transactions on Vehicular Technology, JCR-Q1/Top, IF=6.8) [PDF]
- 基于骨架模态的多级门控图卷积动作识别网络
干创, 吴桂兴*, 詹庆原, 王鹏焜, 彭志磊
计算机科学 2022, 49(1):6 (CCF-B 中文) [PDF]
🏆 Awards
- Bronze, 2022 Global Chinese University Students Data Application Innovation Competition, 2022.
- Second Place, “Innovation Huihu” Outstanding Student Innovation & Entrepreneurship Project, 2022.
- First Place, “Innovation Huihu” Outstanding Student Innovation & Entrepreneurship Project, 2021.
- Honorable Mention, 3/100, Suzhou National Hi-Tech District Innovation & Entrepreneurship Competition, 2021.
- Second Place, Global USTCer Innovation & Entrepreneurship Competition - Suzhou Division, 2021.
- First Place, 1/500, 2021 "Win in Suzhou, Win the Futures" Suzhou Youth Elite Venture Contest.
- First-class Scholarship for Outstanding Students, USTC, 2020, 2021, 2022.
- Award of USTC-GUSU Lab Scholarship, 2021.
- Guanghua Scholarship, USTC, 2021.
- Silver, IEEE-CIS Fraud Detection, Kaggle, 2020.
- Silver, Santander Customer Transaction Prediction, Kaggle, 2020.
- Bronze, Google QUEST Q&A Labeling, Kaggle, 2020.
- Bronze, ASHRAE - Great Energy Predictor III, Kaggle,2020.
- Second Place, "Huawei Cup" China Post-Graduate Mathematical Contest in Modeling, 2019.
- Second-class Scholarship for Outstanding Students, USTC, 2019.
- Individual Scholarship, JLU, 2017.
- Third-class Scholarship for Outstanding Students, JLU, 2016.
- Second Place, China Undergraduate Mathematical Contest in Modeling (Jilin), 2016.
- Outstanding Student Cadre, JLU, 2014.
📖 Educations & Industrial Experiences
- 2018.09 - 2023.06, Ph.D., Data Science, University of Science and Technology of China.
- 2013.09 - 2017.07, Undergraduate, School of Software, Jilin University.
- Algorithm Engineer, Consumer BG Team. Huawei Technologies Co., Ltd. 2019.
- Android Development Engineer, MeMe Live Team. FunPlus. 2017.
📚 Teaching
- 大数据分析, 研究生课程 (软件学院), 2024.02 - 2024.05.
- 数据仓库与数据挖掘, 研究生课程 (软件学院), 2023.09 - 2023.12.
- Teaching Assistant, NVIDIA GTC CHINA 2019.
- Teaching Assistant, NVIDIA GTC CHINA 2018.
🤝 Activities
Conference Committee
- Program Committee Member for ICML 2024
- Program Committee Member for ICLR 2024/2025
- Program Committee Member for NeurIPS 2023/2024
- Program Committee Member for KDD 2022/2023/2024
- Program Committee Member for IJCAI 2024
- Program Committee Member for AAAI 2023/2024/2025
- Program Committee Member for WWW 2024/2025
- Program Committee Member for ECCV 2024
- Program Committee Member for SDM 2024
- Program Committee Member for ECAI 2023
- Program Committee Member for ICME 2024
- Program Committee Member for ICASSP 2024/2025
- Program Committee Member for AISTATS 2025
- Program Committee Member for ACML 2024
- Program Committee Member for Globecom 2024
- Program Committee Member for IJCNN 2023/2024
- Program Committee Member for CSAE 2022
Journal Reviewer
- Reviewer for IEEE Transactions on Emerging Topics in Computational Intelligence
- Reviewer for Scientific Reports
- Reviewer for International Journal of Machine Learning and Cybernetics
- Reviewer for Journal of Advanced Transportation
- Reviewer for Multimedia Systems
- Reviewer for Cluster Computing
- Reviewer for IEEE Open Journal of Signal Processing
- Reviewer for Highlights of Vehicles
- Reviewer for Journal of Artificial Intelligence and Big Data
🤝 Related Links
- Prof. Yang Wang (USTC)
- Prof. Qi Liu (USTC)
- Prof. Zhen Yang (ZJU)
- Prof. Lanzhe Guo (USTC)
- Prof. Guang Wang (FSU)
- Prof. Lei Bai (Shanghai AI Lab)
- Prof. Zhengyang Zhou (USTC)
- Prof. Xu Wang (USTC)
- Prof. Binwu Wang (USTC)
- Dr. Yudong Zhang (USTC)