Jinyu Cai (蔡锦煜)

Jinyu Cai (蔡锦煜)

National University of Singapore

Greetings! I am currently a Postdoc at the Institute of Data Science, National University of Singapore, working with Prof. See-Kiong Ng. Before that, I received my PhD degree at Fuzhou University, supervised by Prof. Wenzhong Guo and Prof. Shiping Wang. From Oct 2021 to Oct 2022, I am a visiting student in the School of Data Science, Chinese University of Hong Kong (Shenzhen), China, supervised by Prof. Jicong Fan. From Jan 2023 to June 2023, I am a visiting student in the Cooperative AI Lab, King’s College London, UK, supervised by Prof. Yali Du. My research interests include anomaly detection, deep clustering, graph neural networks, and generative models . My studies have led to over 20 scientific publications on top-tier conferences and journals, including ICML, NeurIPS, ICLR, CVPR, AAAI, IJCAI, ACM MM, IEEE TMM, PR, etc.

🔥 News

  • 2025.05:  🎉🎉 Two papers have been accepted by ICML2025 (CCF-A)! One of them has been selected as a Spotlight paper (top 2.6% of all submissions). Many thanks to Yunhe and other collaborators.
  • 2025.01:  🎉🎉 I am honored to receive the Best Research Staff Award from the Institute of Data Science (IDS), NUS.
  • 2024.12:  🎉🎉 One paper has been accepted by AAAI 2025 (CCF-A) as an Oral paper! Congrats to Yunhe.
  • 2024.07:  🎉🎉 One paper regarding federated graph anomaly detection has been accepted by ACM MM 2024 (CCF-A)! Many thanks to Yunhe and other collaborators.
  • 2024.04:  🎉🎉 Three papers have been accepted by IJCAI 2024 (CCF-A)! Many thanks to my collaborators.
  • 2024.02:  🎉🎉 One paper has been accepted by TMM (SCI Q1)! Many thanks to my collaborators.
  • 2024.01:  🎉🎉 One paper has been accepted by ICLR2024 (Spotlight)! Congrats to Yunhe and other collaborators.

💼 Work Experience

  • 2023.08 - Now, Postdoc, Institute of Data Science, National University of Singapore, Singapore.

🎓 Educations

  • 2018.09 - 2023.06, Ph.D., College of Computer and Data Science, Fuzhou University, China.
  • 2023.01 - 2023.06, Visiting Ph.D. Student, Cooperative AI Lab, King’s College London, UK.
  • 2021.10 - 2022.10, Visiting Ph.D. Student, School of Data Science, Chinese University of HongKong (Shenzhen), China.
  • 2014.09 - 2018.06, B.E., College of Mathematics and Computer Science, Fuzhou University, China

📝 Academic Service

  • Reviewers
    • IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI)
    • IEEE Transactions on Knowledge and Data Engineering (IEEE TKDE)
    • IEEE Transactions on Image Processing (IEEE TIP)
    • IEEE Transactions on Neural Networks and Learning Systems (IEEE TNNLS)
    • IEEE Transactions on Multimedia (IEEE TMM)
    • IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT)
    • Pattern Recognition
    • Engineering Applications of Artificial Intelligence
  • PC Members
    • NeurIPS 2023/2024/2025
    • ICML 2024/2025
    • ICLR 2024/2025
    • CVPR 2023/2024/2025
    • ICCV 2023/2025
    • ECCV 2024
    • KDD 2024/2025
    • IJCAI 2024/2025
    • AAAI 2025
    • ACM MM 2024/2025

📖 Publications

† indicates co-first author; * indicates corresponding author. Full List

💡 Anomaly Detection

[ICML 2025 Spotlight] Leveraging diffusion model as pseudo-anomalous graph generator for graph-level anomaly detection,
Jinyu Cai, Yunhe Zhang, Fusheng Liu, See-Kiong Ng
Proceedings of the International Conference on Machine Learning. (CCF A)

[ICML 2025] Self-discriminative modeling for anomalous graph detection,
Jinyu Cai, Yunhe Zhang, Jicong Fan
Proceedings of the International Conference on Machine Learning. (CCF A)

[ACM MM 2024] Towards effective federated graph anomaly detection via self-boosted knowledge distillation,
Jinyu Cai, Yunhe Zhang, Zhoumin Lu, Wenzhong Guo, See-Kiong Ng
Proceedings of the 32nd ACM International Conference on Multimedia, Pages 5537-5546, 2024. (CCF A) | [code]

[IJCAI 2024] LG-FGAD: An effective federated graph anomaly detection framework,
Jinyu Cai, Yunhe Zhang, Jicong Fan, See-Kiong Ng
Proceedings of the 33rd International Joint Conference on Artificial Intelligence, Pages 3760-3769, 2024. (CCF A) | [code]

[ICLR 2024] Deep orthogonal hypersphere compression for anomaly detection,
Yunhe Zhang, Yan Sun, Jinyu Cai, Jicong Fan
Proceedings of the 12th International Conference on Learning Representations, 2024. | [code]

[NeurIPS 2022] Perturbation learning based anomaly detection,
Jinyu Cai, Jicong Fan
Advances in Neural Information Processing Systems, 2022. (CCF A) | [code]

💡 Deep Clustering

[AAAI 2025 Oral] Mixture of experts as representation learner for deep multi-view clustering,
Yunhe Zhang, Jinyu Cai*, Zhihao Wu, Pengyang Wang, See-Kiong Ng
Proceedings of the AAAI Conference on Artificial Intelligence, Volume 39(21), Pages 22704-22713, 2025. (CCF A)

[IJCAI 2024] Dual contrastive graph-level clustering with multiple cluster perspectives alignment,
Jinyu Cai, Yunhe Zhang, Jicong Fan, Yali Du, Wenzhong Guo
Proceedings of the 33rd International Joint Conference on Artificial Intelligence, Pages 3770-3779, 2024. (CCF A) | [code]

[CVPR 2022] Efficient deep embedded subspace clustering,
Jinyu Cai, Jicong Fan, Wenzhong Guo, Shiping Wang, Yunhe Zhang, Zhao Zhang
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Pages 1-10, 2022. (CCF A) | [code]

[IEEE TMM] Wasserstein embedding learning for deep clustering: A generative approach,
Jinyu Cai, Yunhe Zhang, Shiping Wang, Jicong Fan, Wenzhong Guo
IEEE Transactions on Multimedia, Volume 26, Pages 7567-7580, 2024. (SCI Q1 CCF B)

[NCAA] Deep graph-level clustering using pseudo-label-guided mutual information maximization network,
Jinyu Cai, Yi Han, Wenzhong Guo, Jicong Fan
Neural Computing and Applications Volume 36(16), Pages 9551-9566 2024.

[PR] Unsupervised deep clustering via contractive feature representation and focal loss,
Jinyu Cai, Shiping Wang, Chaoyang Xu, Wenzhong Guo
Pattern Recognition, Volume 123, 108386, 2022. (SCI Q1 CCF B)

[ESWA] Unsupervised embedded feature learning for deep clustering with stacked sparse auto-encoder,
Jinyu Cai, Shiping Wang, Chaoyang Xu, Wenzhong Guo
Expert Systems with Applications, Volume 186, 115729, 2021. (SCI Q1)

[IEEE TNSE] Towards adaptive masked structural learning for graph-level clustering,
Jinbin Yang, Jinyu Cai†, Yunhe Zhang, Sujia Huang, Shiping Wang
IEEE Transactions on Network Science and Engineering, Volume 12(3), Pages 2021-2032, 2025. (SCI Q1)

[IEEE TCSS] Deep masked graph node clustering,
Jinbin Yang, Jinyu Cai†, Luying Zhong, Yueyang Pi, Shiping Wang
EEE Transactions on Computational Social Systems, Volume 11(6), Pages 7257-7270, 2024. (SCI Q1)

[KBS] Unsupervised embedded feature learning for deep clustering with stacked sparse auto-encoder,
Chaoyang Xu, Renjie Lin, Jinyu Cai, Shiping Wang
Knowledge-Based Systems, Volume 238, 107967, 2022. (SCI Q1)

💡 Others

[IJCAI 2024] Kernel readout for graph neural networks,
Jiajun Yu, Zhihao Wu, Jinyu Cai, Adele Lu Jia, Jicong Fan
Proceedings of the 33rd International Joint Conference on Artificial Intelligence, Pages 2505-2514, 2024. (CCF A)

[INS] Label correction using contrastive prototypical classifier for noisy label learning,
Chaoyang Xu, Renjie Lin, Jinyu Cai, Shiping Wang
Information Sciences, Volume 50(4), 119647, 2023. (CCF C)

[APIN] Unsupervised discriminative feature representation via adversarial auto-encoder,
Wenzhong Guo, Jinyu Cai, Shiping Wang
Applied Intelligence, Volume 50(4), Pages 1155-1171, 2019. (CCF C)

📎 Links