Gerryfan 樊光瑞

Gerryfan 樊光瑞

Lecturer at Taiyuan University of Science and Technology | Ph.D. in Computer Science, Universiti Malaya | Trustworthy learning & decision-making for human–AI and networked systems | 🎾 Tennis - 欢迎约球

Graph-Preference Learning: Debiasing Network-Sampled Human Feedback for Target Welfare Estimation (CCF A)

Published in International Conference on Machine Learning (ICML) 2026, 2026

First-author paper accepted by ICML 2026 on debiasing network-sampled human feedback for target welfare estimation.

Keywords: Graph preference learning, Human feedback, Network sampling, Welfare estimation

Track: Conference Papers

Recommended citation: Fan, G., Liu, D., Sabri, A.Q.M., & Pan, L. (2026). Graph-Preference Learning: Debiasing Network-Sampled Human Feedback for Target Welfare Estimation. In Proceedings of the 43rd International Conference on Machine Learning (ICML 2026). PMLR.