Zhewei Wei (魏哲巍)
魏哲巍
Professor (教授,博导)
Gaoling School of Artificial Intelligence
Renmin University of China
No. 59 Zhongguancun Street, Haidian District, Beijing, 100872, P.R. China
Email:
Phone: (86) 010-62513716
Chinese Homepage (中文主页): gsai.ruc.edu.cn/zhewei
Bio
I am currently a Professor at Gaoling School of Artificial Intelligence, Renmin University of China. I worked as a Professor (Jul 2019 - Jul 2020), and as an Associated Professor (Sep 2014 - Jun 2019) at School of Information, Renmin University of China. I was a Postdoc researcher at MADALGO (Center for Massive Data Algorithmics), Aarhus University, from September 2012 to August 2014, working with Prof. Lars Arge. I was a Postdoc researcher at the Department of Computer Science and Engineering, HKUST, from March to August 2012. I obtained my PhD at Department of Computer Science and Engineering, HKUST in March 2012. My supervisor is Prof. Ke Yi. I received my B.Sc. Degree in the School of Mathematical Sciences at Peking University in June 2008.
Research Interests
My research interests focus on designing simple, elegant, and theoretically guaranteed algorithms to address key challenges in artificial intelligence and large-scale data processing. My specific areas of interest include:
- Large-Scale Graph Computing and Graph Learning: Developing efficient algorithms to process and learn from massive graph structures.
- Stream Data Computing and Learning: Creating algorithms that can handle and learn from continuous, real-time data streams.
- AI for Science: Applying graph learning techniques to solve complex problems in physics, pharmaceuticals, and other scientific fields.
- AI for Social Science: Utilizing large language model (LLM)-based multi-agent systems to model complex human social networks.
- AI for Databases: Leveraging artificial intelligence to optimize database systems for improved performance and efficiency.
News
Sep 26, 2024 | Two papers “Intruding with Words: Towards Understanding Graph Injection Attacks at the Text Level” and “S-MolSearch: 3D Semi-supervised Contrastive Learning for Bioactive Molecule Search” have been accepted by NeurIPS 2024. |
---|---|
Sep 20, 2024 | One paper “SRAP-Agent: Simulating and Optimizing Scarce Resource Allocation Policy with LLM-based Agent” has been accepted by EMNLP 2024 Findings. |
Aug 29, 2024 | The paper “Optimal Matrix Sketching over Sliding Windows” has been awarded “Best Research Paper Nomination” at VLDB 2024! |
Jul 15, 2024 | Two papers “Beyond Over-smoothing: Uncovering the Trainability Challenges in Deep Graph Neural Networks” and “Federated Heterogeneous Contrastive Distillation for Molecular Representation Learning” have been accepted by CIKM 2024. |
May 17, 2024 | One paper “PolyFormer: Scalable Node-wise Filters via Polynomial Graph Transformer” has been accepted by KDD 2024. |
Selected Publications [Full List]
Note: Authors marked with * are the corresponding authors. Papers marked with ** use alphabetic ordering of authors, following the convention of theoretical computer science.Streaming Algorithms
- **Mergeable summariesACM Symposium on Principles of Database Systems (PODS), 2012. (Test of Time Award)
-
Graph Learning
- PolyGCL: GRAPH CONTRASTIVE LEARNING via Learnable Spectral Polynomial FiltersInternational Conference on Learning Representations (ICLR), 2024. (Spotlight)
-
- Convolutional Neural Networks On Graphs With Chebyshev Approximation, RevisitedAnnual Conference on Neural Information Processing Systems (NeurIPS), 2022. (Oral)
-
- Bernnet: Learning Arbitrary Graph Spectral Filters via Bernstein ApproximationAnnual Conference on Neural Information Processing Systems (NeurIPS), 2021
-
- Simple and Deep Graph Convolutional NetworksInternational Conference on Machine Learning (ICML), 2020. (World Artificial Intelligence Conference Youth Outstanding Paper Nomination Award)
-
Graph Algorithms
- **Revisiting Local Computation of PageRank: Simple and OptimalAnnual ACM Symposium on Theory of Computing (STOC), 2024
-
- Personalized PageRank to a Target Node, RevisitedACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2020
-
- Exact Single-Source SimRank Computation on Large GraphsACM Conference on Management of Data (SIGMOD), 2020
-
Data Structures
- Tight Space Bounds for Two-Dimensional Approximate Range CountingACM Transactions on Algorithms (TALG), 2018[TLDR]
-
- Indexing for Summary Queries: Theory and PracticeACM Transactions on Database Systems (TODS), 2014[TLDR]
-
AI for Science
- EquiPocket: an E(3)-Equivariant Geometric Graph Neural Network for Ligand Binding Site PredictionInternational Conference on Machine Learning (ICML), 2024. (Oral)
-
- Uni-Mol: A Universal 3D Molecular Representation Learning FrameworkInternational Conference on Learning Representations (ICLR), 2023[TLDR]
-
Awards
- Best Research Paper Nomination, VLDB 2024
- Young Outstanding Paper Nomination Award, World Artificial Intelligence Conference 2023
- Test of Time Award, PODS 2022
- Young Scientist, Pazhou Laboratory (Huangpu)
- Teaching Model Nomination Award, Renmin University of China, 2019
- "Outstanding Scholar" Young Scholar, Renmin University of China
Services
- Proceedings Chair: SIGMOD/PODS 2020, ICDT 2021
- Area Chair: ICML 2022/2023/2024, NeurIPS 2022/2023, ICLR 2023/2024, TheWebConf 2023
- PC Member: NeurIPS 2021, ICML 2021, KDD 2021, VLDB 2020, ICDE 2021, SIGMETRICS 2020, ICBK 2019, NDBC 2018, ICLR 2023, ICDE 2023
- Conference Reviewer: SODA, ISAAC, VLDB, ICDE, CIKM, PODS, SIGMOD, KDD
- Journal Reviewer: TKDE, TODS, VLDBJ, TOIS, SICOMP, TALG, GEOINFORMATICA, TNNLS, TPAMI
- Member of Journal Editorial Board: IEEE TPAMI Associate Editor, FCS Young Editor
- Members: 中国计算机学会数据库专委会专委,中国计算机学会学术工作委员会委员,人工智能与数字经济广东省实验室(琶洲实验室)青年科学家
Talks
- AI TIME, Matrix Sketching and Streaming Machine Learning (矩阵略图与流数据机器学习), Oct 2024 [video] [slides]
- Academy of Mathematics and System Science, CAS, Graph Convolutional Networks: Theory and Fundamentals, Aug 2024 [slides]
- CCF Young Computer Scientists & Engineers Forum (YOCSEF), AI4DB Algorithm with Theoretical Guarantee (有理论保证的 AI4DB 算法), Aug 2024 [slides]
- Classical Talk@QuACT, Sublinear-Time Algorithms for Random-Walk Probability Estimation, May 2024 [slides]
- VALSE 2023, Graph Representation Learning (图表示学习), June 2023 [slides]
- VALSE 2021, Theoretical Basis of Graph Neural Networks (图神经网络理论基础), Oct 2021 [slides]
Teaching
- Lecturer for Algorithm Design and Analysis (算法设计与分析): Fall 2016, Fall 2017, Fall 2018, Fall 2019, Spring 2020, Fall 2020, Spring 2021, Spring 2022, Spring 2023, Spring 2024
- Lecturer for Graph Machine Learning (图机器学习): Fall 2021, Fall 2022, Fall 2023, Fall 2024
- Lecturer for Seminar for Freshmen (新生研讨课): Fall 2021, Fall 2022, Fall 2023
- Lecturer for ACM-ICPC Algorithms Design: Spring 2019
- Lecturer for ACM-ICPC Algorithms Design: Spring 2018
- Lecturer for Massive Data Algorithms (海量数据算法): Spring 2016, Spring 2017, Spring 2018
- Lecturer for Operational Research (运筹学): Spring 2016
- Lecturer for Calculus: Fall 2015
- Lecturer for Streaming Algorithms and Related Topics: Spring 2014