Fengyuan Yu

Address: Yuquan Campus, 38 Zheda Road, 310027 Hangzhou, Zhejiang, China

Research Areas

Trustworthy AI
Machine Unlearning
Federated Learning
Recommender Systems

I am a third-year Ph.D. student in Computer Science and Technology at Zhejiang University, advised by Assistant Professor Chaochao Chen. I completed my undergraduate study at Turing Class, Chu Kochen Honors College, Zhejiang University, advised by Professor Fan Zhang and Assistant Professor Junbo Zhao.

Research

My current research focuses on verifiable LLM and agent systems, with an emphasis on practical challenges in real-world LLM deployment. In particular, I am working on confidence estimation for LLMs. I am also planning engineering projects on lightweight agent systems. Previously, I studied machine unlearning for generative models and recommender systems. My earlier work covered federated learning, representation learning, and out-of-distribution generalization.

News

Sep 24, 2026	Two papers have been accepted to NeurIPS 2026.
Apr 30, 2026	Our work on optimal fair classification in multi-class settings has been accepted to ICML 2026.
Jan 13, 2026	Our work on generalized embedding learning in federated recommendation has been accepted to The Web Conference 2026.
Nov 08, 2025	Our work on attribute unlearning for user-level federated recommender systems has been accepted to AAAI 2026.
Aug 06, 2025	We’ve released a curated literature repository on generative model unlearning, covering model families, unlearning objectives, methodologies, and evaluation protocols. GitHub: https://github.com/caxLee/Awesome-Generative-Model-Unlearning-Survey Paper: https://arxiv.org/abs/2507.19894.
Jul 05, 2025	Our work on multiple-attribute unlearning for recommender systems has been accepted to ACM MM 2025.

Service

Program Committee Member: AAAI 2027
Reviewer: NeurIPS 2026, ICLR 2027, The Web Conference 2027 (Long Papers)

Selected Publications

A Survey on Generative Model Unlearning: Fundamentals, Taxonomy, Evaluation, and Future Direction

Xiaohua Feng, Jiaming Zhang, Fengyuan Yu, Chengye Wang, Li Zhang, Kaixiang Li, Yuyuan Li, Chaochao Chen^†, and Jianwei Yin

Survey 2025

arXiv preprint arXiv:2507.19894, Jul 2025

Paper Project Page

With the rapid advancement of generative models, associated privacy concerns have attracted growing attention. To address this, researchers have begun adapting machine unlearning techniques from traditional classification models to generative settings. Although notable progress has been made in this area, a unified framework for systematically organizing and integrating existing work is still lacking. The substantial differences among current studies in terms of unlearning objectives and evaluation protocols hinder the objective and fair comparison of various approaches. While some studies focus on specific types of generative models, they often overlook the commonalities and systematic characteristics inherent in Generative Model Unlearning (GenMU). To bridge this gap, we provide a comprehensive review of current research on GenMU and propose a unified analytical framework for categorizing unlearning objectives, methodological strategies, and evaluation metrics. In addition, we explore the connections between GenMU and related techniques, including model editing, reinforcement learning from human feedback, and controllable generation. We further highlight the potential practical value of unlearning techniques in real-world applications. Finally, we identify key challenges and outline future research directions aimed at laying a solid foundation for further advancements in this field. We consistently maintain the related open-source materials at this https URL.
@article{Feng2025GenMU, title = {A Survey on Generative Model Unlearning: Fundamentals, Taxonomy, Evaluation, and Future Direction}, author = {Feng, Xiaohua and Zhang, Jiaming and Yu, Fengyuan and Wang, Chengye and Zhang, Li and Li, Kaixiang and Li, Yuyuan and Chen, Chaochao and Yin, Jianwei}, journal = {arXiv preprint arXiv:2507.19894}, year = {2025}, month = jul, doi = {10.48550/arXiv.2507.19894}, url = {https://arxiv.org/abs/2507.19894}, eprint = {2507.19894}, archiveprefix = {arXiv}, primaryclass = {cs.LG}, topics = {machine-unlearning} }

LEGO: A Lightweight and Efficient Multiple-Attribute Unlearning Framework for Recommender Systems

Fengyuan Yu, Yuyuan Li, Xiaohua Feng, Junjie Fang, Tao Wang, and Chaochao Chen^†

ACM MM 2025

In Proceedings of the 33rd ACM International Conference on Multimedia, Oct 2025

Paper Code

@inproceedings{yu2025lego,
  title = {LEGO: A Lightweight and Efficient Multiple-Attribute Unlearning Framework for Recommender Systems},
  author = {Yu, Fengyuan and Li, Yuyuan and Feng, Xiaohua and Fang, Junjie and Wang, Tao and Chen, Chaochao},
  booktitle = {Proceedings of the 33rd ACM International Conference on Multimedia},
  pages = {6242--6251},
  year = {2025},
  month = oct,
  venue_url = {https://acmmm2025.org/},
  doi = {10.1145/3746027.3755604},
  url = {https://doi.org/10.1145/3746027.3755604},
  topics = {machine-unlearning,recommender-systems}
}

Sharpness-Aware Minimization for Generalized Embedding Learning in Federated Recommendation

Fengyuan Yu, Xiaohua Feng, Yuyuan Li, Changwang Zhang, Jun Wang^†, and Chaochao Chen^†

WWW 2026

In Proceedings of the ACM Web Conference 2026, Apr 2026

Paper Code

@inproceedings{yu2026fedrecgel,
  title = {Sharpness-Aware Minimization for Generalized Embedding Learning in Federated Recommendation},
  author = {Yu, Fengyuan and Feng, Xiaohua and Li, Yuyuan and Zhang, Changwang and Wang, Jun and Chen, Chaochao},
  booktitle = {Proceedings of the ACM Web Conference 2026},
  pages = {6630--6641},
  year = {2026},
  month = apr,
  venue_url = {https://www2026.thewebconf.org/},
  doi = {10.1145/3774904.3792579},
  url = {https://doi.org/10.1145/3774904.3792579},
  topics = {federated-learning,recommender-systems}
}