Currently, Xunkai Li is a second year Ph.D. student of School of Computer Science in Beijing Institute of Technology supervised by Prof. Rong-Hua Li. Prior to that, he received his B.Eng. degree in computer science department from Shandong University in June 2022.
Since 2021, he worked with Prof. Wentao Zhang as a research intern at the Data-centric Machine Learning (DCML) group in the Center of Machine Learning Research at Peking University (PKU).
As an active member of the team, Xunkai is the contributor of scalable graph learning system project SGL 
Email: cs.xunkai.li@gmail.com
Wechat (垎俥): 18045124943
đ đ If you are interested in collaborating with me or want to have a chat, always feel free to contact me through e-mail or WeChat ďźďź
My research interest includes Data-centric Machine Learning and General Graph Learning. I have published some papers at the top international DB/DM/AI conferences such as VLDB, ICDE, WWW, AAAI, IJCAI.
Data-centric Machine Learning: In recent years, AI development has faced challenges, as many leading LLMs still rely on the Transformer architecture. As a result, performance gains have shifted from models to data-focused strategies, particularly in LLM-based Data Optimization.
-
Data Quality: Imbalance, Noise, and Out-Of-Distribution.
-
Data Quantity: Annotation and Augmentation.
-
Data Efficiency: Distillation, Compression, and Selection.
-
Data Privacy: Forgetting and Differential Privacy.
General Graph Learning: Exploring graph learning in complex scenarios is crucial due to the limitations of traditional methods in addressing practical needs. My goal is to advance general graph learning through improved data representation and optimization objectives, particularly in Graph Learning in the era of LLM.
-
High-order Graphs: Directed, Signed, Hypergraphs, Heterophily, Temporal, and LLM-based Rich Text Attribute Graph.
-
Learning Paradigms: Federated, Graph Structure Learning, Knowledge Distillation, Scalability, Unlearning, and LLM-based Collaboration.
đĽ News
- 2024-08: One paper is accepted by VLDB 2025.
- 2024-04: One paper is accepted by IJCAI 2024.
- 2024-03: One paper is accepted by ICDE 2024.
- 2024-02: One paper is accepted by VLDB 2024.
- 2024-01: One paper is accepted by WWW 2024.
- 2023-12: One paper is accepted by AAAI 2024.
- 2023-10: One paper is accepted by ICDE 2024.
- 2023-08: One paper is accepted by VLDB 2023.
đ Publications
# indicates equal contribution
đŻ
Yuchen Meng, Rong-Hua Li, Longlong Lin, Xunkai Li, Gouren Wang
- International Conference on Very Large Data Bases (VLDB), 2025, CCF-A.
đŻ
Xunkai Li, Zhenyu Wu, Wentao Zhang, Henan Sun, Rong-Hua Li, Gouren Wang
- IEEE International Conference on Data Engineering (ICDE), 2024, CCF-A.
đŻ
Xunkai Li#, Yulin Zhao#, Zhengyu Wu, Wentao Zhang, Rong-Hua Li, Gouren Wang
- Association for the Advancement of Artificial Intelligence (AAAI), 2024, CCF-A.
- đđ Oral Presentation
đŻ
Xunkai Li, Jingyuan Ma, Zhengyu Wu, Daohan Su, Wentao Zhang, Rong-Hua Li, Guoren Wang
- The Web Conference (WWW), 2024, CCF-A.
- đđ Oral Presentation
đŻ
Xunkai Li, Meihao Liao, Zhengyu Wu, Daohan Su, Wentao Zhang, Rong-Hua Li, Guoren Wang
- International Conference on Very Large Data Bases (VLDB), 2024, CCF-A.
đŻ
Henan Sun#, Xunkai Li#, Zhengyu Wu, Daohan Su, Rong-Hua Li, Gouren Wang
- IEEE International Conference on Data Engineering (ICDE), 2024, CCF-A.
đŻ
Yinlin Zhu, Xunkai Li, Zhengyu Wu, Di Wu, Miao Hu, Rong-Hua Li
- International Joint Conference on Artificial Intelligence (IJCAI), 2024, CCF-A.
đŻ
Xunkai Li, Zhenyu Wu, Wentao Zhang, Yinlin Zhu, Rong-Hua Li, Guoren Wang
- International Conference on Very Large Data Bases (VLDB), 2023, CCF-A.
Youpeng Hu, Xunkai Li, Yujie Wang, Yixuan Wu, Yining Zhao, Chenggang Yan, Jian Yin, Yue Gao
- IEEE Transactions on Knowledge and Data Engineering (TKDE) 2023, CCF-A.
Xunkai Li#, Ronghui Guo#, Jianwen Chen, Youpeng Hu, Meixia Qu, Bin Jiang
- Neural Computing & Applications (NCAA) 2023, CCF-C.
Haotong Wei, Yinlin Zhu, Xunkai Li, Bin Jiang
- Neural Networks (NN) 2023, CCF-B.
Xin Xiong, Xunkai Li, Youpeng Hu, Yixuan Wu, Jian Yin
- Knowledge and Information Systems (IS) 2022, CCF-B.
Yixuan Wu, Youpeng Hu, Xin Xiong, Xunkai Li, Ronghui Guo, Shuiguang Deng
- Knowledge and Information Systems (KAIS) 2022, CCF-B.
đ Educations
-
2022.09 - 2028.06 (expected), Ph.D. in Computer Science, Beijing Institute of Technology (BIT)
-
2018.09 - 2022.06, B. Eng in Computer Science, Shandong University (SDU)
đŹ Invited Talks
- 2024.08, Oral presentation at IJCAI 2024 about our paper: âFedTAD: Topology-aware Data-free Knowledge Distillation for Subgraph Federated Learningâ.
- 2024.05, Oral presentation at WWW 2024 about our paper: âRethinking Node-wise Propagation for Large-scale Graph Learningâ.
- 2024.05, Oral presentation at ICDE 2024 about our paper: âBreaking the Entanglement of Homophily and Heterophily in Semi-supervised Node Classificationâ and âAdaFGL: A New Paradigm for Federated Node Classification with Topology Heterogeneityâ.
- 2024.02, Oral presentation at AAAI 2024 about our paper: âTowards Effective and General Graph Unlearning via Mutual Evolutionâ.
đ§âđť Service
- Conference Reviewers:
- ICLR, NeurIPS, KDD, WWW
- Journal Reviewers:
- TKDE, TNNLS, TBD
đť Internships
- Research Intern
- Company/Institution: Large Language Model Center, IAAR, Shanghai.
- Advisor: Dr. Zhiyu Li
- Employment period: From 06/2024 to the present
- Research Intern
- Company/Institution: DCML Group, Peking University
- Advisor: Prof. Wentao Zhang
- Employment period: From 10/2021 to the present
- Research Intern
- Company/Institution: iMoon Lab, Tsinghua University
- Advisor: Prof. Yue Gao
- Employment period: From 06/2020 to 06/2021