Publications

Journal Articles

1. A Survey of Geometric Graph Neural Networks: Data Structures, Models and Applications
   Jiaqi Han, Jiacheng Cen, Liming Wu, Zongzhao Li, Xiangzhe Kong, Rui Jiao, Ziyang Yu, Tingyang Xu, Fandi Wu, Zihe Wang, Hongteng Xu, Zhewei Wei, Yang Liu^*, Yu Rong^*, and Wenbing Huang^*
   Frontiers of Computer Science (FCS), 2025
   [arXiv]
2. A Survey of Estimating Number of Distinct Values
   Jiajun Li, Runlin Lei, and Zhewei Wei^*
   Frontiers of Computer Science (FCS), 2025
3. Scalable and Effective Graph Neural Networks via Trainable Random Walk Sampling
   Haipeng Ding, Zhewei Wei^*, and Yuhang Ye
   IEEE Transactions on Knowledge and Data Engineering (TKDE), 2025
4. When Transformer Meets Large Graphs: An Expressive and Efficient Two-View Architecture
   Weirui Kuang, Zhen Wang^*, Zhewei Wei, Yaliang Li, and Bolin Ding
   IEEE Transactions on Knowledge and Data Engineering (TKDE), 2024
5. A Survey of Dynamic Graph Neural Networks
   Yanping Zheng, Lu Yi, and Zhewei Wei^*
   Frontiers of Computer Science (FCS), 2024
   [arXiv]
6. A Survey on Large Language Model Based Autonomous Agents
   Lei Wang, Chen Ma, Xueyang Feng, Zeyu Zhang, Hao Yang, Jingsen Zhang, Zhiyuan Chen, Jiakai Tang, Xu Chen^*, Yankai Lin^*, Wayne Xin Zhao, Zhewei Wei, and Ji-Rong Wen
   Frontiers of Computer Science (FCS), 2024
   [arXiv]
7. Efficient Algorithms for Personalized PageRank Computation: A Survey

   Mingji Yang, Hanzhi Wang, Zhewei Wei^*, Sibo Wang, and Ji-Rong Wen

   IEEE Transactions on Knowledge and Data Engineering (TKDE), 2024

   [arXiv]

   In this survey paper, we give a systematic and comprehensive review of several basic techniques and recent algorithms for PPR computation from an algorithmic perspective.

8. Index-Free Triangle-Based Graph Local Clustering
   Zhe Yuan, Zhewei Wei^*, Fangrui Lv, and Ji-Rong Wen
   Frontiers of Computer Science (FCS), 2024
9. Enabling Efficient Random Access to Hierarchically Compressed Text Data on Diverse GPU Platforms
   Yihua Hu, Feng Zhang^*, Yifei Xia, Zhiming Yao, Letian Zeng, Haipeng Ding, Zhewei Wei, Xiao Zhang, Jidong Zhai, Xiaoyong Du, and Siqi Ma
   IEEE Transactions on Parallel and Distributed Systems (TPDS), 2023
10. Influence Maximization Revisited: Efficient Sampling with Bound Tightened
    Qintian Guo, Sibo Wang^*, Zhewei Wei^*, Wenqing Lin, and Jing Tang
    ACM Transactions on Database Systems (TODS), 2022
11. Persistent Summaries

    Tianjing Zeng, Zhewei Wei^*, Ge Luo, Ke Yi, Xiaoyong Du, and Ji-Rong Wen

    ACM Transactions on Database Systems (TODS), 2022

    We propose the persistent summaries for streaming algorithms, enabling them to answer queries about the streaming data at any prior time.

12. Building Graphs at Scale via Sequence of Edges: Model and Generation Algorithms
    Yu Liu, Lei Zou^*, and Zhewei Wei
    IEEE Transactions on Knowledge and Data Engineering (TKDE), 2022
    [Code]
13. ExactSim: Benchmarking Single-Source SimRank Algorithms with High-Precision Ground Truths
    Hanzhi Wang, Zhewei Wei, Yu Liu, Ye Yuan, Xiaoyong Du, and Ji-Rong Wen
    The VLDB Journal, 2021
    [Code]
14. A Game-Based Framework for Crowdsourced Data Labeling
    Jingru Yang, Ju Fan^*, Zhewei Wei, Guoliang Li, Tongyu Liu, and Xiaoyong Du
    The VLDB Journal, 2020
15. Efficient Algorithms for Approximate Single-Source Personalized PageRank Queries
    Sibo Wang, Renchi Yang, Runhui Wang, Xiaokui Xiao, Zhewei Wei^*, Wenqing Lin, Yin Yang, and Nan Tang
    ACM Transactions on Database Systems (TODS), 2019
    [arXiv] [Code]
16. Parallel Trajectory-to-Location Join
    Shuo Shang, Lisi Chen, Kai Zheng^*, Christian S. Jensen, Zhewei Wei, and Panos Kalnis
    IEEE Transactions on Knowledge and Data Engineering (TKDE), 2019
17. Distribution-Aware Crowdsourced Entity Collection
    Ju Fan, Zhewei Wei, Dongxiang Zhang, Jingru Yang, and Xiaoyong Du
    IEEE Transactions on Knowledge and Data Engineering (TKDE), 2019
18. Tight Space Bounds for Two-Dimensional Approximate Range Counting

    Zhewei Wei and Ke Yi

    ACM Transactions on Algorithms (TALG), 2018

    We study the problem of two-dimensional orthogonal range counting with additive error and give tight space bounds.

19. Parallel Trajectory Similarity Joins in Spatial Networks
    Shuo Shang, Lisi Chen^*, Zhewei Wei, Christian S. Jensen, Kai Zheng, and Panos Kalnis
    The VLDB Journal, 2018
20. Optimal Algorithms for Selecting Top-k Combinations of Attributes: Theory and Applications
    Chunbin Lin, Jiaheng Lu, Zhewei Wei, Jianguo Wang, and Xiaokui Xiao
    The VLDB Journal, 2017
21. Dynamic Shortest Path Monitoring in Spatial Networks
    Shuo Shang, Lisi Chen, Zhewei Wei, Danhuai Guo^*, and Ji-Rong Wen
    Journal of Computer Science and Technology (JCST), 2016
22. Collective Travel Planning in Spatial Networks
    Shuo Shang, Lisi Chen, Zhewei Wei, Christian S Jensen, Ji-Rong Wen, and Panos Kalnis
    IEEE Transactions on Knowledge and Data Engineering (TKDE), 2015
23. Indexing for Summary Queries: Theory and Practice

    Ke Yi, Lu Wang, and Zhewei Wei

    ACM Transactions on Database Systems (TODS), 2014

    We design efficient indexing techniques that enable extracting statistical summaries, such as frequent items, quantiles, and sketches with linear space requirements and optimal or near-optimal query cost.

24. **Cache-Oblivious Hashing
    Rasmus Pagh, Zhewei Wei, Ke Yi, and Qin Zhang
    Algorithmica, 2013
25. **Mergeable Summaries
    Pankaj K Agarwal, Graham Cormode, Zengfeng Huang, Jeff M Phillips, Zhewei Wei, and Ke Yi^*
    ACM Transactions on Database Systems (TODS), 2013

Conference Articles

1. **PageRank Centrality in Directed Graphs with Bounded In-Degree
   Mikkel Thorup, Hanzhi Wang, Zhewei Wei, and Mingji Yang
   To appear in ACM-SIAM Symposium on Discrete Algorithms (SODA), 2026
   [arXiv]
2. Future Link Prediction Without Memory or Aggregation
   Lu Yi, Runlin Lei, Fengran Mo, Yanping Zheng^*, Zhewei Wei^*, and Yuhang Ye
   Annual Conference on Neural Information Processing Systems (NeurIPS), 2025
   [arXiv]
3. Lighter-X: An Efficient and Plug-and-play Strategy for Graph-based Recommendation through Decoupled Propagation
   Yanping Zheng, Zhewei Wei^*, Frank de Hoog, Xu Chen, Hongteng Xu, Yuhang Ye, and Jiadeng Huang
   International Conference on Very Large Data Bases (VLDB), 2025
4. LLM-Based Multi-Agent Systems are Scalable Graph Generative Models
   Jiarui Ji, Runlin Lei, Jialing Bi, Zhewei Wei^*, Xu Chen, Yankai Lin, Xuchen Pan, Yaliang Li, and Bolin Ding
   The 63rd Annual Meeting of the Association for Computational Linguistics (ACL Findings), 2025
   [arXiv] [Code]
5. TIDFormer: Exploiting Temporal and Interactive Dynamics Makes A Great Dynamic Graph Transformer
   Jie Peng, Zhewei Wei^*, and Yuhang Ye
   ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2025
6. Position: Spectral GNNs Rely Less on Graph Fourier Basis than Conceived
   Yuhe Guo, Huayi Tang, Jiahong Ma, Hongteng Xu, and Zhewei Wei^*
   International Conference on Machine Learning (ICML), 2025
7. Dimension-Free Adaptive Subgradient Methods with Frequent Directions
   Sifan Yang, Yuanyu Wan, Peijia Li, Yibo Wang, Xiao Zhang, Zhewei Wei, and Lijun Zhang
   International Conference on Machine Learning (ICML), 2025
8. Fast Second-Order Online Kernel Learning through Incremental Matrix Sketching and Decomposition
   Dongxie Wen, Xiao Zhang, and Zhewei Wei
   International Joint Conference on Artificial Intelligence (IJCAI), 2025
   [arXiv]
9. Long-term Spatio-Temporal Forecasting using Spectral Graph Neural Networks
   Xiang Li, Yanping Zheng, Zhewei Wei, and Ye Yuan
   International Joint Conference on Neural Networks (IJCNN), 2025
10. NeutronTask: Scalable and Efficient Multi-GPU GNN Training with Task Parallelism
    Zhenbo Fu, Xin Ai, Qiange Wang, Yanfeng Zhang, Shizhan Lu, Chaoyi Chen, Chunyu Cao, Hao Yuan, Zhewei Wei, Yu Gu, Yingyou Wen, and Ge Yu
    International Conference on Very Large Data Bases (VLDB), 2025
    [Code]
11. Efficiency Unleashed: Inference Acceleration for LLM-based Recommender Systems with Speculative Decoding
    Yunjia Xi, Hangyu Wang, Bo Chen, Jianghao Lin, Menghui Zhu, Weiwen Liu, Ruiming Tang, Zhewei Wei, Weinan Zhang, and Yong Yu
    International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), 2025
    [arXiv]
12. **Simple and Optimal Algorithms for Heavy Hitters and Frequency Moments in Distributed Models
    Zengfeng Huang, Hongzheng Xiong, Xiaoyi Zhu, and Zhewei Wei
    Annual ACM Symposium on Theory of Computing (STOC), 2025
    [arXiv]
13. Scalable and Certifiable Graph Unlearning: Overcoming the Approximation Error Barrier
    Lu Yi and Zhewei Wei
    International Conference on Learning Representations (ICLR), 2025. (Spotlight, 5.1%)
    [arXiv]
14. TGB-Seq Benchmark: Challenging Temporal GNNs with Complex Sequential Dynamics
    Lu Yi, Jie Peng, Yanping Zheng, Fengran Mo, Zhewei Wei, Yuhang Ye, Yue Zixuan, and Zengfeng Huang
    International Conference on Learning Representations (ICLR), 2025
    [arXiv] [Code] [Website]
15. Advancing Retrosynthesis with Retrieval-Augmented Graph Generation
    Anjie Qiao, Zhen Wang, Jiahua Rao, Yuedong Yang, and Zhewei Wei^*
    AAAI Conference on Artificial Intelligence (AAAI), 2025. (Oral)
16. Mixing Time Matters: Accelerating Effective Resistance Estimation via Bidirectional Method
    Guanyu Cui, Hanzhi Wang, and Zhewei Wei^*
    ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2025
    [arXiv] [Code] [Poster] [Slides]
17. Large-Scale Spectral Graph Neural Networks via Laplacian Sparsification
    Haipeng Ding, Zhewei Wei^*, and Yuhang Ye
    ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2025
    [arXiv]
18. PRICE: A Pretrained Model for Cross-Database Cardinality Estimation
    Tianjing Zeng, Junwei Lan, Jiahong Ma, Wenqing Wei, Rong Zhu^*, Pengfei Li, Bolin Ding^*, Defu Lian, Zhewei Wei, and Jingren Zhou^*
    International Conference on Very Large Data Bases (VLDB), 2025
    [arXiv] [Code]
19. Intruding with Words: Towards Understanding Graph Injection Attacks at the Text Level
    Runlin Lei, Yuwei Hu, Yuchen Ren, and Zhewei Wei^*
    Annual Conference on Neural Information Processing Systems (NeurIPS), 2024
    [arXiv] [Code]
20. S-MolSearch: 3D Semi-supervised Contrastive Learning for Bioactive Molecule Search
    Gengmo Zhou, Zhen Wang, Feng Yu, Guolin Ke, Zhewei Wei^*, and Zhifeng Gao^*
    Annual Conference on Neural Information Processing Systems (NeurIPS), 2024
    [arXiv] [Code]
21. SRAP-Agent: Simulating and Optimizing Scarce Resource Allocation Policy with LLM-Based Agent
    Jiarui Ji, Yang Li, Hongtao Liu, Zhicheng Du, Zhewei Wei, Qi Qi, Weiran Shen, and Yankai Lin^*
    Conference on Empirical Methods in Natural Language Processing (EMNLP Findings), 2024
    [arXiv] [Code]
22. Beyond Over-smoothing: Uncovering the Trainability Challenges in Deep Graph Neural Networks
    Jie Peng, Runlin Lei, and Wei* Zhewei
    ACM International Conference on Information and Knowledge Management (CIKM), 2024
    [arXiv]
23. Federated Heterogeneous Contrastive Distillation for Molecular Representation Learning
    Jinjia Feng, Zhen Wang, Zhewei Wei^*, Yaliang Li, Bolin Ding, and Hongteng Xu
    ACM International Conference on Information and Knowledge Management (CIKM), 2024
24. PolyFormer: Scalable Node-wise Filters via Polynomial Graph Transformer
    Jiahong Ma, Mingguo He, and Zhewei Wei^*
    ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2024
    [arXiv] [Code]
25. EquiPocket: an E(3)-Equivariant Geometric Graph Neural Network for Ligand Binding Site Prediction

    Yang Zhang, Zhewei Wei^*, Ye Yuan, Chongxuan Li, and Wenbing Huang^*

    International Conference on Machine Learning (ICML), 2024. (Oral)

    [arXiv] [Code]

    We propose EquiPocket, the first equivariant GNN-based method for ligand binding site prediction.

26. Optimal Matrix Sketching over Sliding Windows

    Hanyan Yin, Dongxie Wen, Jiajun Li, Zhewei Wei^*, Xiao Zhang, Zengfeng Huang, and Feifei Li

    International Conference on Very Large Data Bases (VLDB), 2024. (Best Paper Nomination)

    [arXiv] [Code] [Poster] [Slides]

    We introduce the DS-FD algorithm, which achieves the optimal \(O\left(d/\varepsilon\right)\) space bound to maintain a sketch \(\boldsymbol{B}∈\mathbb{R}^{O\left({1\over\varepsilon}\right)\times d}\) of a matrix \(\boldsymbol{A}∈\mathbb{R}^{W \times d}\) consisting of the most recent \(d\)-dimension rows of a data stream in the row-update, \(W\)-sized sliding window model, with a covariance error bound of \(\lVert \boldsymbol{A}^⊤\boldsymbol{A}-\boldsymbol{B}^⊤\boldsymbol{B}\rVert_2\le \varepsilon \lVert \boldsymbol{A}\rVert_F^2\).

27. HierAffinity: Predicting Protein-Ligand Binding Affinity With Hierarchical Modeling
    Yang Zhang, Zhewei Wei^*, Wenbing Huang^*, and Chongxuan Li
    International Conference on Database Systems for Advanced Applications (DASFAA), 2024
28. TransPocket: Structural and Geometric Transformer for Ligand Binding Site Detection
    Yang Zhang, Zhewei Wei^*, Wenbing Huang^*, and Chongxuan Li
    International Conference on Database Systems for Advanced Applications (DASFAA), 2024
29. Learning-based Property Estimation with Polynomials
    Jiajun Li, Runlin Lei, Sibo Wang, Zhewei Wei^*, and Bolin Ding
    ACM Conference on Management of Data (SIGMOD), 2024
    [Code]
30. **Revisiting Local Computation of PageRank: Simple and Optimal

    Hanzhi Wang, Zhewei Wei^*, Ji-Rong Wen, and Mingji Yang

    Annual ACM Symposium on Theory of Computing (STOC), 2024

    [arXiv] [Video] [Slides]

    We use simple techniques and analyses to give matching upper and lower bounds for estimating PageRank contributions and single-node PageRank. Our results for the upper bounds are derived by revisiting the known algorithms of ApproxContributions (a.k.a. Backward Push) and BiPPR.

31. Exploring Neural Scaling Law and Data Pruning Methods For Node Classification on Large-scale Graphs
    Zhen Wang, Yaliang Li, Bolin Ding, Yule Li, and Zhewei Wei
    The Web Conference (WWW), 2024. (Oral)
    [Code]
32. Spectral Heterogeneous Graph Convolutions via Positive Noncommutative Polynomials
    Mingguo He, Zhewei Wei^*, Shikun Feng, Zhengjie Huang, Weibin Li, Yu Sun, and Dianhai Yu
    The Web Conference (WWW), 2024. (Oral)
    [arXiv] [Code]
33. PolyGCL: GRAPH CONTRASTIVE LEARNING via Learnable Spectral Polynomial Filters

    Jingyu Chen, Runlin Lei, and Zhewei Wei^*

    International Conference on Learning Representations (ICLR), 2024. (Spotlight)

    [Code]

    We propose POLYGCL, a GCL pipeline that utilizes polynomial filters to achieve contrastive learning between the low-pass and highpass views.

34. **Approximating Single-Source Personalized PageRank with Absolute Error Guarantees
    Zhewei Wei^*, Ji-Rong Wen, and Mingji Yang
    International Conference on Database Theory (ICDT), 2024
    [arXiv]
35. Do Deep Learning Methods Really Perform Better in Molecular Conformation Generation?
    Gengmo Zhou, Zhifeng Gao, Zhewei Wei, Hang Zheng, and Guolin Ke^*
    International Conference on Learning Representations (ICLR), 2023. (MLDD Oral)
    [arXiv] [Code]
36. Estimating Single-Node PageRank in \(\tilde{O}\left(\min\{d_t, \sqrt{m}\}\right)\)Time
    Hanzhi Wang and Zhewei Wei^*
    International Conference on Very Large Data Bases (VLDB), 2023
    [arXiv] [Code]
37. MGNN: Graph Neural Networks Inspired by Distance Geometry Problem
    Guanyu Cui and Zhewei Wei^*
    ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2023
    [arXiv] [Code] [Poster] [Slides]
38. Optimal Dynamic Subset Sampling: Theory and Applications
    Lu Yi, Hanzhi Wang, and Zhewei Wei^*
    ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2023
    [arXiv] [Poster] [Slides]
39. Clenshaw Graph Neural Networks
    Yuhe Guo and Zhewei Wei^*
    ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2023
    [arXiv] [Code]
40. Graph Neural Networks with Learnable and Optimal Polynomial Bases
    Yuhe Guo and Zhewei Wei^*
    International Conference on Machine Learning (ICML), 2023
    [arXiv] [Code]
41. **On Range Summary Queries
    Peyman Afshani, Pingan Cheng, Aniket Basu Roy, and Zhewei Wei
    International Colloquium on Automata, Languages and Programming (ICALP), 2023
    [arXiv]
42. Decoupled Graph Neural Networks for Large Dynamic Graphs
    Yanping Zheng, Zhewei Wei^*, and Jiajun Liu
    International Conference on Very Large Data Bases (VLDB), 2023
    [arXiv] [Code]
43. Uni-Mol: A Universal 3D Molecular Representation Learning Framework

    Gengmo Zhou, Zhifeng Gao^*, Qiankun Ding, Hang Zheng, Hongteng Xu, Zhewei Wei, Linfeng Zhang, and Guolin Ke^*

    International Conference on Learning Representations (ICLR), 2023

    [ChemRxiv] [Code]

    Uni-Mol is the first pure 3D molecular pretraining framework that can predict 3D positions, and the first molecular pretraining framework that can be directly used in 3D tasks in the field of drug design.

44. Personalized PageRank on Evolving Graphs with an Incremental Index-Update Scheme
    Guanhao Hou, Qintian Guo, Fangyuan Zhang, Sibo Wang^*, and Zhewei Wei
    ACM Conference on Management of Data (SIGMOD), 2023
    [arXiv]
45. Preformer: Predictive Transformer with Multi-Scale Segment-Wise Correlations for Long-Term Time Series Forecasting
    Dazhao Du, Bing Su^*, and Zhewei Wei
    IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023
    [arXiv] [Code]
46. Evennet: Ignoring Odd-Hop Neighbors Improves Robustness of Graph Neural Networks
    Runlin Lei, Zhen Wang, Yaliang Li, Bolin Ding, and Zhewei Wei^*
    Annual Conference on Neural Information Processing Systems (NeurIPS), 2022
    [arXiv] [Code]
47. Convolutional Neural Networks On Graphs With Chebyshev Approximation, Revisited

    Mingguo He, Zhewei Wei^*, and Ji-Rong Wen

    Annual Conference on Neural Information Processing Systems (NeurIPS), 2022. (Oral)

    [arXiv] [Code]

    We revisit the problem of approximating the spectral graph convolutions with Chebyshev polynomials and then propose ChebNetII, a new GNN model based on Chebyshev interpolation, which enhances the original Chebyshev polynomial approximation while reducing the Runge phenomenon.

48. Approximating Probabilistic Group Steiner Trees in Graphs
    Shuang Yang, Yahui Sun^*, Jiesong Liu, Xiaokui Xiao, Rong-Hua Li, and Zhewei Wei
    International Conference on Very Large Data Bases (VLDB), 2022
    [Code]
49. MGMAE: Molecular Representation Learning by Reconstructing Heterogeneous Graphs with A High Mask Ratio
    Jinjia Feng, Zhen Wang, Yaliang Li, Bolin Ding, Zhewei Wei^*, and Hongteng Xu
    ACM International Conference on Information and Knowledge Management (CIKM), 2022
50. Optimizing Random Access to Hierarchically-Compressed Data on GPU
    Feng Zhang, Yihua Hu, Haipeng Ding, Zhiming Yao, Zhewei Wei, Xiao Zhang^*, and Xiaoyong Du
    International Conference for High Performance Computing, Networking, Storage, and Analysis (SC), 2022
51. Sampling-based Estimation of the Number of Distinct Values in Distributed Environment
    Jiajun Li, Zhewei Wei^*, Bolin Ding, Xiening Dai, Lu Lu, and Jingren Zhou
    ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2022
    [arXiv] [Code]
52. Graph Neural Networks with Node-wise Architecture
    Zhen Wang, Zhewei Wei, Yaliang Li^*, Weirui Kuang, and Bolin Ding
    ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2022
53. Instant Graph Neural Networks for Dynamic Graphs
    Yanping Zheng, Hanzhi Wang, Zhewei Wei^*, Jiajun Liu, and Sibo Wang
    ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2022
    [arXiv] [Code]
54. Edge-based Local Push for Personalized PageRank
    Hanzhi Wang, Zhewei Wei^*, Junhao Gan, Ye Yuan, Xiaoyong Du, and Ji-Rong Wen
    International Conference on Very Large Data Bases (VLDB), 2022
    [arXiv] [Code]
55. Building Graphs at Scale via Sequence of Edges: Model and Generation Algorithms
    Yu Liu, Lei Zou, and Zhewei Wei
    IEEE International Conference on Data Engineering (ICDE), 2022
56. Predicting Protein-Ligand Binding Affinity via Joint Global-Local Interaction Modeling
    Yang Zhang, Gengmo Zhou, Zhewei Wei, and Hongteng Xu
    IEEE International Conference on Data Mining (ICDM), 2022
    [arXiv]
57. Learning to be a Statistician: Learned Estimator for Number of Distinct Values
    Renzhi Wu, Bolin Ding, Xu Chu, Zhewei Wei, Xiening Dai, Tao Guan, and Jingren Zhou
    International Conference on Very Large Data Bases (VLDB), 2021
    [arXiv] [Code]
58. BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation

    Mingguo He, Zhewei Wei^*, Zengfeng Huang, and Hongteng Xu^*

    Annual Conference on Neural Information Processing Systems (NeurIPS), 2021

    [arXiv] [Code]

    We propose the BernNet, a graph neural network that provides a simple and intuitive mechanism for designing and learning an arbitrary spectral filter via Bernstein polynomial approximation.

59. Approximate Graph Propagation
    Hanzhi Wang, Mingguo He, Zhewei Wei^*, Sibo Wang, Ye Yuan, Xiaoyong Du, and Ji-Rong Wen
    ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2021
    [arXiv] [Code] [Slides]
60. Graph Neural Networks Inspired by Classical Iterative Algorithms
    Yongyi Yang, Tang Liu, Yangkun Wang, Jinjing Zhou, Quan Gan, Zhewei Wei, Zheng Zhang, Zengfeng Huang^*, and David Wipf^*
    International Conference on Machine Learning (ICML), 2021. (Long Talk)
    [arXiv] [Code]
61. Massively Parallel Algorithms for Personalized PageRank
    Guanhao Hou, Xingguang Chen, Sibo Wang^*, and Zhewei Wei^*
    International Conference on Very Large Data Bases (VLDB), 2021
62. Unifying the Global and Local Approaches: An Efficient Power Iteration with Forward Push
    Hao Wu, Junhao Gan^*, Zhewei Wei^*, and Rui Zhang
    ACM Conference on Management of Data (SIGMOD), 2021
    [arXiv] [Code]
63. FlashP: An Analytical Pipeline for Real-time Forecasting of Time-Series Relational Data
    Shuyuan Yan, Bolin Ding^*, Wei Guo, Jingren Zhou, Zhewei Wei, Xiaowei Jiang, and Sheng Xu
    International Conference on Very Large Data Bases (VLDB), 2021
    [arXiv]
64. Scalable Graph Neural Networks via Bidirectional Propagation
    Ming Chen, Zhewei Wei^*, Bolin Ding, Yaliang Li, Ye Yuan, Xiaoyong Du, and Ji-Rong Wen
    Annual Conference on Neural Information Processing Systems (NeurIPS), 2020
    [arXiv] [Code] [Poster] [Slides]
65. SimTab: Accuracy-Guaranteed SimRank Queries Through Tighter Confidence Bounds and Multi-Armed Bandits
    Yu Liu, Lei Zou, Qian Ge, and Zhewei Wei^*
    International Conference on Very Large Data Bases (VLDB), 2020
66. Simple and Deep Graph Convolutional Networks

    Ming Chen, Zhewei Wei^*, Zengfeng Huang, Bolin Ding, and Yaliang Li

    International Conference on Machine Learning (ICML), 2020. (World Artificial Intelligence Conference Youth Outstanding Paper Nomination Award)

    [arXiv] [Code]

    We propose the GCNII, an extension of the vanilla GCN model with two simple yet effective techniques: Initial residual and Identity mapping.

67. Personalized PageRank to a Target Node, Revisited

    Hanzhi Wang, Zhewei Wei^*, Junhao Gan, Sibo Wang, and Zengfeng Huang

    ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2020

    [arXiv] [Code] [Slides]

    We propose Randomized Backward Search (RBS), a novel algorithm that answers approximate single-target personalized PageRank queries (also known as PageRank contribution queries) with nearly optimal time complexity.

68. Influence Maximization Revisited: Efficient Reverse Reachable Set Generation with Bound Tightened
    Qintian Guo, Sibo Wang^*, Zhewei Wei^*, and Ming Chen
    ACM Conference on Management of Data (SIGMOD), 2020
69. Exact Single-Source SimRank Computation on Large Graphs

    Hanzhi Wang, Zhewei Wei^*, Ye Yuan, Xiaoyong Du, and Ji-Rong Wen

    ACM Conference on Management of Data (SIGMOD), 2020

    [arXiv] [Code] [Slides]

    We propose ExactSim, the first algorithm that enables probabilistic exact single-source SimRank queries on large graphs. ExactSim can provide the ground truth with a precision up to 7 decimal places for single-source SimRank queries on large graphs within a reasonable query time.

70. CrowdGame: A Game-Based Crowdsourcing System for Cost-Effective Data Labeling
    Tongyu Liu, Jingru Yang, Ju Fan^*, Zhewei Wei, Guoliang Li, and Xiaoyong Du
    ACM Conference on Management of Data (SIGMOD), 2019
71. Scalable Graph Embeddings via Sparse Transpose Proximities
    Yuan Yin and Zhewei Wei^*
    ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2019. (Oral)
    [arXiv] [Code] [Poster] [Slides]
72. Efficient Estimation of Heat Kernel PageRank for Local Clustering
    Renchi Yang, Xiaokui Xiao, Zhewei Wei^*, Sourav S Bhowmick, Jun Zhao, and Rong-Hua Li
    ACM Conference on Management of Data (SIGMOD), 2019
    [arXiv]
73. PRSim: Sublinear Time SimRank Computation on Large Power-Law Graphs
    Zhewei Wei, Xiaodong He, Xiaokui Xiao, Sibo Wang, Yu Liu, Xiaoyong Du, and Ji-Rong Wen^*
    ACM Conference on Management of Data (SIGMOD), 2019
    [arXiv] [Code] [Poster] [Slides]
74. Cost-Effective Data Annotation using Game-Based Crowdsourcing
    Jingru Yang, Ju Fan^*, Zhewei Wei, Guoliang Li, Tongyu Liu, and Xiaoyong Du
    International Conference on Very Large Data Bases (VLDB), 2018
75. TopPPR: Top-k Personalized PageRank Queries with Precision Guarantees on Large Graphs
    Zhewei Wei, Xiaodong He, Xiaokui Xiao, Sibo Wang, Shuo Shang^*, and Ji-Rong Wen^*
    ACM Conference on Management of Data (SIGMOD), 2018
    [Code] [Poster] [Slides]
76. **Independent Range Sampling, Revisited
    Peyman Afshani and Zhewei Wei^*
    European Symposium on Algorithms (ESA), 2017
77. Trajectory Similarity Join in Spatial Networks
    Shuo Shang, Lisi Chen, Zhewei Wei, Christian S. Jensen, Kai Zheng, and Panos Kalnis
    International Conference on Very Large Data Bases (VLDB), 2017
    [Poster]
78. ProbeSim: Scalable Single-Source and Top-k SimRank Computations on Dynamic Graphs
    Yu Liu, Bolong Zheng, Xiaodong He, Zhewei Wei^*, Xiaokui Xiao, Kai Zheng, and Jiaheng Lu
    International Conference on Very Large Data Bases (VLDB), 2017
    [arXiv] [Code] [Poster] [Slides]
79. Collective Travel Planning in Spatial Networks
    Shuo Shang, Lisi Chen, Zhewei Wei, Christian S. Jensen, Ji-Rong Wen, and Panos Kalnis
    IEEE International Conference on Data Engineering (ICDE), 2017
80. Tracking Matrix Approximation over Distributed Sliding Windows
    Haida Zhang, Zengfeng Huang, Zhewei Wei, Wenjie Zhang, and Xuemin Lin
    IEEE International Conference on Data Engineering (ICDE), 2017
81. FORA: Simple and Effective Approximate Single-Source Personalized PageRank
    Sibo Wang, Renchi Yang, Xiaokui Xiao, Zhewei Wei^*, and Yin Yang
    ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2017
    [Code] [Poster] [Slides]
82. Matrix Sketching Over Sliding Windows
    Zhewei Wei, Xuancheng Liu, Feifei Li, Shuo Shang, Xiaoyong Du, and Ji-Rong Wen^*
    ACM Conference on Management of Data (SIGMOD), 2016
    [Poster] [Slides]
83. Towards Maximum Independent Sets on Massive Graphs
    Yu Liu, Jiaheng Lu, Hua Yang, Xiaokui Xiao, and Zhewei Wei
    International Conference on Very Large Data Bases (VLDB), 2015
    [Code] [Poster] [Slides]
84. Persistent Data Sketching
    Zhewei Wei, Ge Luo, Ke Yi, Xiaoyong Du, and Ji-Rong Wen
    ACM Conference on Management of Data (SIGMOD), 2015
    [Poster] [Slides]
85. **Equivalence between Priority Queues and Sorting in External Memory
    Zhewei Wei and Ke Yi
    European Symposium on Algorithms (ESA), 2014
    [arXiv] [Slides]
86. **The Space Complexity of 2-Dimensional Approximate Range Counting
    Zhewei Wei and Ke Yi
    ACM-SIAM Symposium on Discrete Algorithms (SODA), 2013
    [arXiv] [Slides]
87. **Mergeable Summaries

    Pankaj K. Agarwal, Graham Cormode, Zengfeng Huang, Jeff Phillips, Zhewei Wei, and Ke Yi

    ACM Symposium on Principles of Database Systems (PODS), 2012. (Test of Time Award)

    [Poster] [Slides]

    We study the mergeability of data summaries and propose methods to make summaries mergeable while preserving error and size guarantees.

88. **Beyond Simple Aggregates: Indexing for Summary Queries
    Zhewei Wei and Ke Yi
    ACM Symposium on Principles of Database Systems (PODS), 2011
    [Slides]
89. **Cache-Oblivious Hashing

    Rasmus Pagh, Zhewei Wei, Ke Yi, and Qin Zhang

    ACM Symposium on Principles of Database Systems (PODS), 2010

    [Slides]

    We investigate the construction of cache-oblivious hash table and study the linear probing and block probing algorithms in cache-oblivious settings.

90. **Dynamic External Hashing: The Limit of Buffering
    Zhewei Wei, Ke Yi, and Qin Zhang
    ACM Symposium on Parallelism in Algorithms and Architectures (SPAA), 2009
    [arXiv]

Theses

1. Classic and New Data Structure Problems in External Memory
   Zhewei Wei
   PhD Dissertation, Hong Kong University of Science and Technology, defended on February 2, 2012
2. Hashing Based Dictionaries in Different Memory Models
   Zhewei Wei
   PhD Qualifying Exam Survey, 2010

Preprints

1. **On Solving Asymmetric Diagonally Dominant Linear Systems in Sublinear Time
   Tsz Chiu Kwok, Zhewei Wei, and Mingji Yang
   arXiv, 2025
2. Exploring the Potential of Large Language Models as Predictors in Dynamic Text-Attributed Graphs
   Runlin Lei, Jiarui Ji, Haipeng Ding, Lu Yi, Zhewei Wei, Yongchao Liu, and Chuntao Hong
   arXiv, 2025
3. Matrix Sketching in Bandits: Current Pitfalls and New Framework
   Dongxie Wen, Hanyan Yin, Xiao Zhang, and Zhewei Wei
   arXiv, 2024
4. Scalable and Accurate Graph Reasoning with LLM-based Multi-Agents
   Yuwei Hu, Runlin Lei, Xinyi Huang, Zhewei Wei, and Yongchao Liu
   arXiv, 2024
5. Rethinking GNN Expressive Power from a Distributed Computational Model Perspective
   Guanyu Cui, Yuhe Guo, Zhewei Wei, and Hsin-Hao Su
   arXiv, 2024
6. Very Large-Scale Multi-Agent Simulation in AgentScope
   Xuchen Pan, Dawei Gao, Yuexiang Xie, Zhewei Wei, Yaliang Li, Bolin Ding, Ji-Rong Wen, and Jingren Zhou
   arXiv, 2024