Rui Wang (汪睿)

Rui Wang (汪睿)

ZJU100 Research Fellow

Publications

You can also find my articles on my Google Scholar profile.

FlareDTDG: Harnessing Temporal Recency for Scalable Discrete-Time Dynamic Graph Training.

Published in PVLDB, 2026

This paper is about a distributed discrete-time dynamic graphs framework.

Recommended citation: Wenjie Huang, Rui Wang, Jing Cao, Tongya Zheng, Xinyu Wang, Mingli Song, Sai Wu, Chun Chen, "FlareDTDG: Harnessing Temporal Recency for Scalable Discrete-Time Dynamic Graph Training." the 52st International Conference on Very Large Data Bases (PVLDB 2026), London, United Kingdom, September 1-5, 2026

SALoM: Structure Aware Temporal Graph Networks with Long-Short Memory Updater.

Published in NeurIPS, 2025

This paper is about an effective memory-based temporal GNN model.

Recommended citation: Hanwen Liu, Longjiao Zhang, Rui Wang, Tongya Zheng, Sai Wu, Chang Yao, Mingli Song, "SALoM: Structure Aware Temporal Graph Networks with Long-Short Memory Updater." the Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS 2025), San Diego Convention Center, Nov 30th to Dec 7th, 2025

Efficient Distributed Graph Neural Network Training with Source Chunking and Moving Aggregation.

Published in TKDE, 2025

This paper is about an efficient distributed GNN training system.

Recommended citation: Wenjie Huang, Tongya Zheng, Rui Wang*, Tongtian Zhu, Bingde Hu, Shuibing He, Mingli Song, Xinyu Wang, Sai Wu, Chun Chen. "Efficient Distributed Graph Neural Network Training with Source Chunking and Moving Aggregation." IEEE Transactions on Knowledge and Data Engineering (TKDE) 2025

XDB: A Task-Centric AI-Native DBMS for Model Management and Inference.

Published in SIGMOD, 2025

This paper is about an AI-native DBMS for model management and inference.

Recommended citation: Sai Wu, Ruichen Xia, Dingyu Yang, Rui Wang, Huihang Lai, Jiarui Guan, Jiameng Bai, Dongxiang Zhang, Xiu Tang, Zhongle Xie, Peng Lu, Gang Chen. "XDB: A Task-Centric AI-Native DBMS for Model Management and Inference." The ACM Special Interest Group on Management of Data (SIGMOD 2026) 2026

PTWalker: Cache-Efficient Random Walks via Alternating Dual-Subgraph Walker Updating.

Published in ICPP, 2025

This paper is about a cache-efficient random walk framework specifically designed for RWPT.

Recommended citation: Shuai Lin, Rui Wang, Zaigui zhang, Long Deng, Wenzhe Zhu, Yongkun Li, Yinlong Xu. "PTWalker: Cache-Efficient Random Walks via Alternating Dual-Subgraph Walker Updating." The 54th International Conference on Parallel Processing (ICPP 2025), San Diego, CA, September 8 -11, 2025.

Effective and Efficient Distributed Temporal Graph Learning through Hotspot Memory Sharing.

Published in PVLDB, 2025

This paper is about an efficient distributed memory-based temporal GNN training and inference system.

Recommended citation: Longjiao Zhang, Rui Wang, Tongya Zheng, Ziqi Huang, Wenjie Huang, Xinyu Wang, Can Wang, Mingli Song, Sai Wu, Shuibing He, "Effective and Efficient Distributed Temporal Graph Learning through Hotspot Memory Sharing." the 51st International Conference on Very Large Data Bases (PVLDB 2025), London, United Kingdom, September 1-5, 2025

DualGuard: A Parameter Space Transformation Approach for Bidirectional Defense in Split-Based LLM Fine-Tuning.

Published in ACL, 2025

This paper is about a bidirectional defense mechanism tailored for split- based LLM-FT scenarios.

Recommended citation: Zihan Liu, Yizhen Wang, Rui Wang, Sai Wu, "DualGuard: A Parameter Space Transformation Approach for Bidirectional Defense in Split-Based LLM Fine-Tuning." the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), Vienna, Austria, July 27 to August 1st, 2025.

Efficient Dynamic Graph Learning with Refined Batch Parallel Training.

Published in IJCAI, 2025

This paper is about a refined batch parallel training framework designed for efficient dynamic graph learning.

Recommended citation: Zhengzhao Feng, Rui Wang, Longjiao Zhang, Tongya Zheng, Ziqi Huang, Mingli Song, "Efficient Dynamic Graph Learning with Refined Batch Parallel Training." the 34th International Joint Conference on Artificial Intelligence (IJCAI 2025), Montreal, 16th – 22nd August, 2025.

Quick Sense Temporal Graph Transformer with Effective Representation Augmentation.

Published in IJCNN, 2025

This paper is about a solution designed to enhance local sensation ability and accelerate training efficiency in temporal graph transformers.

Recommended citation: Ziqi Huang, Tongya Zheng, Rui Wang, Longjiao Zhang, Wenjie Huang, Xinyu Wang, "Quick Sense Temporal Graph Transformer with Effective Representation Augmentation." the International Joint Conference on Neural Networks (IJCNN 2025), ROME, ITALY, June 30 - July 5, 2025.

Enumeration of Billions of Maximal Bicliques in Bipartite Graphs without Using GPUs.

Published in IEEE SC, 2024

This paper is about a highly-efficient CPU solution for the maximal biclique enumeration problem.

Recommended citation: Zhe Pan, Shuibing He, Xu Li, Xuechen Zhang, Yanlong Yin, Rui Wang, Lidan Shou, Mingli Song, Xian-He Sun, and Gang Chen. Enumeration of Billions of Maximal Bicliques in Bipartite Graphs without Using GPUs. In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC 2024). Atlanta, GA, USA, 2024, pp. 1-15 https://dl.acm.org/doi/abs/10.1145/3545008.3545060

Two-Dimensional Balanced Partitioning and Efficient Caching for Distributed Graph Analysis.

Published in IEEE TPDS, 2024

This paper is about a graph partitioning and caching scheme for distributed graph systems.

Recommended citation: Shuai Lin, Rui Wang, Yongkun Li, Yinlong Xu, John C.S. Lui. "Two-Dimensional Balanced Partitioning and Efficient Caching for Distributed Graph Analysis," in IEEE Transactions on Parallel and Distributed Systems, vol. 36, no. 2, pp. 133-149, Feb. 2025. https://ieeexplore.ieee.org/abstract/document/10756620

AMBEA: Aggressive Maximal Biclique Enumeration in Large Bipartite Graph Computing.

Published in IEEE TC, 2024

This paper is about a aggressive set-enumeration tree for the maximal biclique enumeration problem.

Recommended citation: Zhe Pan, Xu Li, Shuibing He, Xuechen Zhang, Rui Wang, Yunjun Gao, Gang Chen and Xian-He Sun. "AMBEA: Aggressive Maximal Biclique Enumeration in Large Bipartite Graph Computing," in IEEE Transactions on Computers (IEEE TC), vol. 73, no. 12, pp. 2664-2677, Dec. 2024. https://ieeexplore.ieee.org/abstract/document/10633882

Efficient Large Graph Processing with Chunk-Based Graph Representation Model.

Published in USENIX ATC, 2024

This paper is about an I/O-efficient graph system designed for processing large-scale graphs on NVMe SSDs.

Recommended citation: Rui Wang, Weixu Zong, Shuibing He, Xinyu Chen, Zhenxin Li, and Zheng Dang "Efficient Large Graph Processing with Chunk-Based Graph Representation Model." USENIX Annual Technical Conference (ATC 2024), Santa Clara, CA, pp.1239-1255, 2024. https://www.usenix.org/conference/atc24/presentation/wang-rui

CCL-BTree: A Crash-Consistent Locality-Aware B+-Tree for Reducing XPBuffer-Induced Write Amplification in Persistent Memory.

Published in ACM EuroSys, 2024

This paper is about a crash-consistent locality-aware B+-Tree that reduces the number of flushes to the PM media.

Recommended citation: Zhenxin Li, Shuibing He, Zheng Dang, Peiyi Hong, Xuechen Zhang, Rui Wang, and Fei Wu. CCL-BTree: A Crash-Consistent Locality-Aware B+-Tree for Reducing XPBuffer-Induced Write Amplification in Persistent Memory. In Proceedings of the Nineteenth European Conference on Computer Systems (EuroSys 2024). Association for Computing Machinery, New York, NY, USA, 441–455. https://dl.acm.org/doi/abs/10.1145/3627703.3629582

Efficient Maximal Biclique Enumeration on GPUs.

Published in IEEE SC, 2023

This paper is about a highly-efficient GPU solution for the maximal biclique enumeration problem.

Recommended citation: Zhe Pan, Shuibing He, Xu Li, Xuechen Zhang, Rui Wang, and Gang Chen. Efficient Maximal Biclique Enumeration on GPUs. In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC 2023). Association for Computing Machinery, New York, NY, USA, Article 16, 1–13. https://dl.acm.org/doi/abs/10.1145/3545008.3545060

XPGraph: XPline-Friendly Persistent Memory Graph Stores for Large-Scale Evolving Graphs.

Published in IEEE/ACM MICRO, 2022

This paper is about a PMEM-based graph storage system for managing large-scale evolving graphs.

Recommended citation: Rui Wang, Shuibing He, Weixu Zong, Yongkun Li, and Yinlong Xu. "XPGraph: XPline-friendly persistent memory graph stores for large-scale evolving graphs." In 2022 55th IEEE/ACM International Symposium on Microarchitecture (MICRO), pp. 1308-1325. IEEE, 2022. https://ieeexplore.ieee.org/abstract/document/9923828

Towards Fast Large-scale Graph Analysis via Two-dimensional Balanced Partitioning.

Published in ICPP, 2022

This paper is about a two-phase graph partition scheme to realize two-dimensional balance for both vertices and edges.

Recommended citation: Shuai Lin, Rui Wang, Yongkun Li, Yinlong Xu, John C.S. Lui, Fei Chen, Pengcheng Wang, and Lei Han. Towards Fast Large-scale Graph Analysis via Two-dimensional Balanced Partitioning. In Proceedings of the 51st International Conference on Parallel Processing (ICPP 2022). Association for Computing Machinery, New York, NY, USA, Article 37, 1–11. https://dl.acm.org/doi/abs/10.1145/3545008.3545060

Common Neighbors Matter: Fast Random Walk Sampling With Common Neighbor Awareness.

Published in IEEE TKDE, 2022

This paper is about a common neighbor aware random walk framework.

Recommended citation: Rui Wang, Yongkun Li, Shuai Lin, WeiJie Wu, Hong Xie, Yinlong Xu, and John CS Lui. "Common Neighbors Matter: Fast Random Walk Sampling With Common Neighbor Awareness," in IEEE Transactions on Knowledge and Data Engineering, vol. 35, no. 5, pp. 4570-4584, 1 May 2023 https://ieeexplore.ieee.org/abstract/document/9712235

On Modeling Influence Maximization in Social Activity Networks under General Settings.

Published in ACM TKDD, 2021

This paper is about an influence maximization algorithm in social activity networks based on random wakls.

Recommended citation: Rui Wang, Yongkun Li, Shuai Lin, Hong Xie, Yinlong Xu, and John C. S. Lui. On Modeling Influence Maximization in Social Activity Networks under General Settings. ACM Trans. Knowl. Discov. Data (ACM TKDD),vol.15, no.6, 2021 \https://dl.acm.org/doi/abs/10.1145/3451218

GraphWalker: An I/O-Efficient and Resource-Friendly Graph Analytic System for Fast and Scalable Random Walks.

Published in USENIX ATC, 2020

This paper is about an I/O-efficient out-of-core graph system for random walks.

Recommended citation: Rui Wang, Yongkun Li, Hong Xie, Yinlong Xu, and John CS Lui. "GraphWalker: An I/O-Efficient and Resource-Friendly Graph Analytic System for Fast and Scalable Random Walks." In 2020 USENIX Annual Technical Conference (USENIX ATC 20), pp. 559-571. 2020. https://www.usenix.org/conference/atc20/presentation/wang-rui