Hi, I'm Zekai Chen.

I am currently with Beijing Institute of Technology (BIT). My research focuses on Graph Machine Learning, particularly federated, multimodal, and foundation-model settings.

I am interested in building graph learning systems that can learn from decentralized, heterogeneous, multimodal, and privacy-sensitive data, as well as applying graph learning to scientific discovery.

My complete publication record is also available on Google Scholar.

Research Interests

Federated Graph Learning Multi-Agent System Multimodal Learning Graph Foundation Models AI for Science

News

2026
MagicDock was accepted as a Regular Paper at ICML 2026.
2026
DANCE was accepted as a Regular Paper at ICML 2026.
Jun. 2026
PRISM, our work on topology-aware cross-modal imputation for modality-deficient federated graph learning, became publicly available.
May 2026
STAGE, our work on tackling semantic drift in multimodal federated graph learning, became publicly available.
2025
Rethinking Client-oriented Federated Graph Learning was published at CIKM 2025.

Selected Publications

MagicDock: Toward Docking-oriented De Novo Ligand Design via Gradient Inversion
Zekai Chen, Xunkai Li, Sirui Zhang, Henan Sun, Jia Li, Zhenjun Li, Bing Zhou, Rong-Hua Li, Guoren Wang
ICML 2026 Regular Paper · International Conference on Machine Learning
[Paper]
DANCE: Dynamic, Available, Neighbor-gated Condensation for Federated Text-Attributed Graphs
Zekai Chen, Haodong Lu, Xunkai Li, Henan Sun, Jia Li, Hongchao Qin, Rong-Hua Li, Guoren Wang
ICML 2026 Regular Paper · International Conference on Machine Learning
[Paper]
Rethinking Client-oriented Federated Graph Learning
Zekai Chen, Xunkai Li, Yinlin Zhu, Rong-Hua Li, Guoren Wang
CIKM 2025 Method: FedC4
[Paper] [Code]
STAGE: Tackling Semantic Drift in Multimodal Federated Graph Learning
Zekai Chen, Xun Wu, Xunkai Li, Yihan Sun, Rong-Hua Li, Guoren Wang
2026 Multimodal Federated Graph Learning
[Paper]
PRISM: Topology-Aware Cross-Modal Imputation for Modality-Deficient Federated Graph Learning
Zekai Chen, Miao Zhang, Jiayang Xing, Xunkai Li, Xun Wu, Rong-Hua Li, Guoren Wang
2026 Multimodal Federated Graph Learning
[Paper]

→ View all publications

Publications

2026
MMFGU: Multimodal Federated Graph Unlearning
Haodong Lu, Zekai Chen, Weiwei Ji, Shihao Li, Xunkai Li, Xun Wu, Yinlin Zhu, Rong-Hua Li
arXiv 2026 Preprint
[Paper]
FedOGL: Combating Catastrophic Forgetting in Federated Open-World Multimodal Graph Learning
Zekai Chen, Haodong Lu, Shihao Li, Weiwei Ji, Xunkai Li, Xun Wu, Yinlin Zhu, Rong-Hua Li
arXiv 2026 Preprint
[Paper]
FedLAB: Traceable Semantic Codebooks for Federated Multimodal Graph Foundation Learning
Zekai Chen, Kairui Yang, Xuaner Chen, Xunkai Li, Xun Wu, Rong-Hua Li, Guoren Wang
arXiv 2026 Preprint
[Paper]
PRISM: Topology-Aware Cross-Modal Imputation for Modality-Deficient Federated Graph Learning
Zekai Chen, Miao Zhang, Jiayang Xing, Xunkai Li, Xun Wu, Rong-Hua Li, Guoren Wang
arXiv 2026 Preprint
[Paper]
Towards Robust Federated Multimodal Graph Learning under Modality Heterogeneity
Sirui Zhang, Haonan Wang, Xunkai Li, Zekai Chen, Shumeng Li, Hongchao Qin, Rong-Hua Li, Guoren Wang
arXiv 2026 FedMPO
[Paper]
STAGE: Tackling Semantic Drift in Multimodal Federated Graph Learning
Zekai Chen, Xun Wu, Xunkai Li, Yihan Sun, Rong-Hua Li, Guoren Wang
arXiv 2026 Preprint
[Paper]
MagicDock: Toward Docking-oriented De Novo Ligand Design via Gradient Inversion
Zekai Chen, Xunkai Li, Sirui Zhang, Henan Sun, Jia Li, Zhenjun Li, Bing Zhou, Rong-Hua Li, Guoren Wang
ICML 2026 Regular Paper · International Conference on Machine Learning
[Paper]
DANCE: Dynamic, Available, Neighbor-gated Condensation for Federated Text-Attributed Graphs
Zekai Chen, Haodong Lu, Xunkai Li, Henan Sun, Jia Li, Hongchao Qin, Rong-Hua Li, Guoren Wang
ICML 2026 Regular Paper · International Conference on Machine Learning
[Paper]
OpenDDI: A Comprehensive Benchmark for DDI Prediction
Xinmo Jin, Bowen Fan, Xunkai Li, Henan Sun, YuXin Zeng, Zekai Chen, Yuxuan Sun, Jia Li, Qiangqiang Dai, Hongchao Qin, Rong-Hua Li, Guoren Wang
arXiv 2026 Preprint
[Paper] [Code]
LION: A Clifford Neural Paradigm for Multimodal-Attributed Graph Learning
Xunkai Li, Zhengyu Wu, Zekai Chen, Henan Sun, Daohan Su, Guang Zeng, Hongchao Qin, Rong-Hua Li, Guoren Wang
arXiv 2026 Preprint
[Paper]
BoostFGL: Boosting Fairness in Federated Graph Learning
Zekai Chen, Kairui Yang, Xunkai Li, Henan Sun, Zhihan Zhang, Jia Li, Qiangqiang Dai, Rong-Hua Li, Guoren Wang
arXiv 2026 Preprint
[Paper]
2025
Rethinking Client-oriented Federated Graph Learning
Zekai Chen, Xunkai Li, Yinlin Zhu, Rong-Hua Li, Guoren Wang
CIKM 2025 Conference on Information and Knowledge Management · Method: FedC4
[Paper] [Code]
A Comprehensive Data-centric Overview of Federated Graph Learning
Zhengyu Wu, Xunkai Li, Yinlin Zhu, Zekai Chen, Guochen Yan, Yanyu Yan, Hao Zhang, Yuming Ai, Xinmo Jin, Rong-Hua Li, Guoren Wang
arXiv 2025 Survey / Preprint
[Paper]

→ Google Scholar profile

Contact

For research discussions and collaborations, please feel free to contact me.

Email: zackchen02@163.com