Flint Xiaofeng Fan

@a-star.edu.sg

Scientist at A*STAR Centre for Frontier AI Research (A*STAR CFAR)
A*STAR Centre for Frontier AI Research (A*STAR CFAR)

Flint Xiaofeng Fan


                        Download Compact PDF  
https://researchid.co/fan.xiaofeng

RESEARCH, TEACHING, or OTHER INTERESTS

Artificial Intelligence
12

Scopus Publications

317

Scholar Citations

8

Scholar h-index

8

Scholar i10-index

Scopus Publications

  • Unveiling and Mitigating Untargeted Poisoning Attacks on Federated Knowledge Graph Embedding
    Wenzheng Jiang, Ke Liang, Wenke Huang, Xiongtao Zhang, Zhenxing Xu, Guancheng Wan, Cheston Tan, Flint Xiaofeng Fan, Ji Wang
    Www 2026 Proceedings of the ACM Web Conference 2026, 2026
  • Position Paper: Rethinking Privacy in RL for Sequential Decision-making in the Age of LLMs
    Flint Xiaofeng Fan, Cheston Tan, Roger Wattenhofer, Yew-Soon Ong
    Proceedings of the International Joint Conference on Neural Networks, 2025
    The rise of reinforcement learning (RL) in critical real-world applications demands a fundamental rethinking of privacy in AI systems. Traditional privacy frameworks, designed to protect isolated data points, fall short for sequential decision-making systems where sensitive information emerges from temporal patterns, behavioral strategies, and collaborative dynamics. Modern RL paradigms, such as federated RL (FedRL) and RL with human feedback (RLHF) in large language models (LLMs), exacerbate these challenges by introducing complex, interactive, and context-dependent learning environments that traditional methods do not address. In this position paper, we argue for a new privacy paradigm built on four core principles: multi-scale protection, behavioral pattern protection, collaborative privacy preservation, and context-aware adaptation. These principles expose inherent tensions between privacy, utility, and interpretability that must be navigated as RL systems become more pervasive in high-stakes domains like healthcare, autonomous vehicles, and decision support systems powered by LLMs. To tackle these challenges, we call for the development of new theoretical frameworks, practical mechanisms, and rigorous evaluation methodologies that collectively enable effective privacy protection in sequential decision-making systems.
  • FedRLHF: A Convergence-Guaranteed Federated Framework for Privacy-Preserving and Personalized RLHF
    Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems Aamas, 2025
  • Revisiting the Byzantine Resilience of Federated Reinforcement Learning: A Distillation Perspective
    Wenzheng Jiang, Ji Wang, Zhengyi Zhong, Jiangzhou Liao, Xiaomin Zhu, Flint Xiaofeng Fan
    Proceedings of the IEEE International Conference on Trust Security and Privacy in Computing and Communications Trustcom, 2025
    Federated reinforcement learning (FRL) enhances sample efficiency while preserving data privacy. However, standard FRL frameworks rely on aggregating model parameters or gradients, making them vulnerable to Byzantine attacks. Current Byzantine-resilient approaches primarily focus on server-side robust aggregations, leaving the fundamental vulnerability of transmitting parameters unaddressed. In this paper, we revisit Byzantine resilience in FRL from the knowledge distillation (KD) perspective. KD-based FRL uploads policy representations instead of policy parameters. This framework-level shift fundamentally constrains the attack surface. We theoretically prove traditional FRL suffers unbounded corruption from Byzantine agents, whereas KD-based FRL converges to an ${\mathcal{O}}(\alpha )$-stationary point under α-fraction adversaries, formalizing the accuracy-robustness trade-off. Empirical validation confirms the Byzantine resilience of KD-based FRL: it maintains near-optimal performance across diverse attacks and even withstands Byzantine fractions up to 0.9. Our theoretical guarantees and experiments demonstrate distillation endows FRL with fundamentally stronger resilience.
  • FedHPD: Heterogeneous Federated Reinforcement Learning via Policy Distillation
    Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems Aamas, 2025
  • Diversifying Policy Behaviors via Extrinsic Behavior Curiosity
    Proceedings of Machine Learning Research, 2025
  • SUBER: An RL Environment with Simulated Human Behavior for Recommender Systems
    Nathan Corecco, Giorgio Piatti, Luca A. Lanzendörfer, Flint Xiaofeng Fan, Roger Wattenhofer
    Frontiers in Artificial Intelligence and Applications, 2024
    Reinforcement learning (RL) has gained popularity in the realm of recommender systems due to its ability to optimize long-term rewards and guide users in discovering relevant content. However, the successful implementation of RL in recommender systems is challenging because of several factors, including the limited availability of online data for training on-policy methods. This scarcity requires expensive human interaction for online model training. Furthermore, the development of effective evaluation frameworks that accurately reflect the quality of models remains a fundamental challenge in recommender systems. To address these challenges, we propose a comprehensive framework for synthetic environments that simulate human behavior by harnessing the capabilities of large language models (LLMs). We complement our framework with in-depth ablation studies and demonstrate its effectiveness with experiments on movie and book recommendations. Using LLMs as synthetic users, this work introduces a modular and novel framework to train RL-based recommender systems. The software, including the RL environment, is publicly available on https://github.com/SUBER-Team/SUBER.
  • Decentralized Federated Policy Gradient with Byzantine Fault-Tolerance and Provably Fast Convergence
    Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems Aamas, 2024
  • Federated sequential decision making: Bayesian optimization, reinforcement learning, and beyond
    Zhongxiang Dai, Flint Xiaofeng Fan, Cheston Tan, Trong Nghia Hoang, Bryan Kian Hsiang Low, Patrick Jaillet
    Federated Learning Theory and Practice, 2024
  • FedHQL: Federated Heterogeneous Q-Learning
    Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems Aamas, 2023
  • FEDERATED NEURAL BANDITS
    11th International Conference on Learning Representations Iclr 2023, 2023
  • Fault-Tolerant Federated Reinforcement Learning with Theoretical Guarantee
    Advances in Neural Information Processing Systems, 2021

RECENT SCHOLAR PUBLICATIONS

  • Unveiling and Mitigating Untargeted Poisoning Attacks on Federated Knowledge Graph Embedding
    W Jiang, K Liang, W Huang, X Zhang, Z Xu, G Wan, C Tan, FX Fan, ...
    Proceedings of the ACM Web Conference 2026, 2569-2580 , 2026
    2026
  • Why Do We Suffer for Fun? Ordeal Pleasure in Souls-like Games
    FX Fan
    arXiv preprint arXiv:2603.26677 , 2026
    2026
  • Information fidelity in tool-using llm agents: A martingale analysis of the model context protocol
    FX Fan, C Tan, R Wattenhofer, YS Ong
    arXiv preprint arXiv:2602.13320 , 2026
    2026
    Citations: 2
  • Provably Reliable Tool-Using LLM Agents: Formal Guarantees on Error Accumulation in the Model Context Protocol (MCP)
    FX Fan, C Tan, R Wattenhofer, YS Ong
    2026
  • Revisiting the Byzantine Resilience of Federated Reinforcement Learning: A Distillation Perspective
    W Jiang, J Wang, Z Zhong, J Liao, X Zhu, FX Fan
    2025 IEEE 24th International Conference on Trust, Security and Privacy in … , 2025
    2025
  • Position Paper: Rethinking Privacy in RL for Sequential Decision-making in the Age of LLMs
    FX Fan, C Tan, R Wattenhofer, YS Ong
    International Joint Conference on Neural Networks (IJCNN) 2025 , 2025
    2025
    Citations: 6
  • FedHPD: Heterogeneous Federated Reinforcement Learning via Policy Distillation
    W Jiang, J Wang, X Zhang, W Bao, C Tan, FX Fan
    International Conference on Autonomous Agents and Multiagent Systems (AAMAS … , 2025
    2025
    Citations: 7
  • FedRLHF: A Convergence-Guaranteed Federated Framework for Privacy-Preserving and Personalized RLHF
    FX Fan, C Tan, YS Ong, R Wattenhofer, WT Ooi
    International Conference on Autonomous Agents and Multiagent Systems (AAMAS … , 2024
    2024
    Citations: 20
  • From Myth to Market: Lessons from Black Myth: Wukong's Success
    FX Fan
    Digital Games Research Association (DiGRA) 2025 , 2024
    2024
    Citations: 6
  • Diversifying Policy Behaviors with Extrinsic Behavioral Curiosity
    Z Wan, X Yu, DM Bossens, Y Lyu, Q Guo, FX Fan, YS Ong, I Tsang
    arXiv preprint arXiv:2410.06151 , 2024
    2024
    Citations: 4
  • An LLM-based Recommender System Environment
    N Corecco, G Piatti, LA Lanzendörfer, FX Fan, R Wattenhofer
    KDD 2024 workshop on Generative AI for Recommender Systems and Personalization , 2024
    2024
    Citations: 10
  • CAESAR: Enhancing Federated RL in Heterogeneous MDPs through Convergence-Aware Sampling with Screening
    HY Mak, FX Fan, LA Lanzendörfer, C Tan, WT Ooi, R Wattenhofer
    AAMAS 2024 workshop on Adaptive and Learning Agents (ALA 2024) , 2024
    2024
    Citations: 8
  • Decentralized Federated Policy Gradient with Byzantine Fault-Tolerance and Provably Fast Convergence
    P Jordan, F Grötschla, FX Fan, R Wattenhofer
    International Conference on Autonomous Agents and Multiagent Systems (AAMAS … , 2024
    2024
    Citations: 12
  • Chapter 14-Federated sequential decision making: Bayesian optimization, reinforcement learning, and beyond
    Z Dai, FX Fan, C Tan, TN Hoang, BKH Low, P Jaillet
    Federated Learning. Academic Press , 2024
    2024
    Citations: 3
  • Federated sequential decision making: Bayesian optimization, reinforcement learning, and beyond
    Z Dai, FX Fan, C Tan, TN Hoang, BKH Low, P Jaillet
    Federated Learning, 257-279 , 2024
    2024
    Citations: 6
  • Quality diversity imitation learning
    Z Wan, X Yu, DM Bossens, Y Lyu, Q Guo, FX Fan, I Tsang
    2024
    Citations: 7
  • SUBER: An RL Environment with Simulated Human Behavior for Recommender Systems
    N Corecco, G Piatti, LA Lanzendörfer, FX Fan, R Wattenhofer
    European Conference on Artificial Intelligence (ECAI) 2024 , 2023
    2023
    Citations: 17
  • Reinforcement Learning of TSP Heuristics with Message Passing Neural Networks
    L Holbein, Y Schmid
    ETH (MSc) student thesis , 2023
    2023
  • Action and Trajectory Planning for Urban Autonomous Driving with Hierarchical Reinforcement Learning
    X Lu, FX Fan, T Wang
    ICML 2023 Workshop Frontiers4LCD , 2023
    2023
    Citations: 19
  • FedHQL: Federated Heterogeneous Q-Learning
    FX Fan, Y Ma, Z Dai, C Tan, BKH Low, R Wattenhofer
    International Conference on Autonomous Agents and Multiagent Systems (AAMAS … , 2023
    2023
    Citations: 24

MOST CITED SCHOLAR PUBLICATIONS

  • Fault-tolerant federated reinforcement learning with theoretical guarantee
    X Fan, Y Ma, Z Dai, W Jing, C Tan, BKH Low
    Advances in neural information processing systems (NeurIPS) 2021 , 2021
    2021
    Citations: 126
  • Federated neural bandit
    Z Dai, Y Shu, A Verma, FX Fan, BKH Low, P Jaillet
    International Conference on Learning Representations (ICLR) 2023 , 2022
    2022
    Citations: 40
  • FedHQL: Federated Heterogeneous Q-Learning
    FX Fan, Y Ma, Z Dai, C Tan, BKH Low, R Wattenhofer
    International Conference on Autonomous Agents and Multiagent Systems (AAMAS … , 2023
    2023
    Citations: 24
  • FedRLHF: A Convergence-Guaranteed Federated Framework for Privacy-Preserving and Personalized RLHF
    FX Fan, C Tan, YS Ong, R Wattenhofer, WT Ooi
    International Conference on Autonomous Agents and Multiagent Systems (AAMAS … , 2024
    2024
    Citations: 20
  • Action and Trajectory Planning for Urban Autonomous Driving with Hierarchical Reinforcement Learning
    X Lu, FX Fan, T Wang
    ICML 2023 Workshop Frontiers4LCD , 2023
    2023
    Citations: 19
  • SUBER: An RL Environment with Simulated Human Behavior for Recommender Systems
    N Corecco, G Piatti, LA Lanzendörfer, FX Fan, R Wattenhofer
    European Conference on Artificial Intelligence (ECAI) 2024 , 2023
    2023
    Citations: 17
  • Decentralized Federated Policy Gradient with Byzantine Fault-Tolerance and Provably Fast Convergence
    P Jordan, F Grötschla, FX Fan, R Wattenhofer
    International Conference on Autonomous Agents and Multiagent Systems (AAMAS … , 2024
    2024
    Citations: 12
  • An LLM-based Recommender System Environment
    N Corecco, G Piatti, LA Lanzendörfer, FX Fan, R Wattenhofer
    KDD 2024 workshop on Generative AI for Recommender Systems and Personalization , 2024
    2024
    Citations: 10
  • CAESAR: Enhancing Federated RL in Heterogeneous MDPs through Convergence-Aware Sampling with Screening
    HY Mak, FX Fan, LA Lanzendörfer, C Tan, WT Ooi, R Wattenhofer
    AAMAS 2024 workshop on Adaptive and Learning Agents (ALA 2024) , 2024
    2024
    Citations: 8
  • FedHPD: Heterogeneous Federated Reinforcement Learning via Policy Distillation
    W Jiang, J Wang, X Zhang, W Bao, C Tan, FX Fan
    International Conference on Autonomous Agents and Multiagent Systems (AAMAS … , 2025
    2025
    Citations: 7
  • Quality diversity imitation learning
    Z Wan, X Yu, DM Bossens, Y Lyu, Q Guo, FX Fan, I Tsang
    2024
    Citations: 7
  • Position Paper: Rethinking Privacy in RL for Sequential Decision-making in the Age of LLMs
    FX Fan, C Tan, R Wattenhofer, YS Ong
    International Joint Conference on Neural Networks (IJCNN) 2025 , 2025
    2025
    Citations: 6
  • From Myth to Market: Lessons from Black Myth: Wukong's Success
    FX Fan
    Digital Games Research Association (DiGRA) 2025 , 2024
    2024
    Citations: 6
  • Federated sequential decision making: Bayesian optimization, reinforcement learning, and beyond
    Z Dai, FX Fan, C Tan, TN Hoang, BKH Low, P Jaillet
    Federated Learning, 257-279 , 2024
    2024
    Citations: 6
  • Diversifying Policy Behaviors with Extrinsic Behavioral Curiosity
    Z Wan, X Yu, DM Bossens, Y Lyu, Q Guo, FX Fan, YS Ong, I Tsang
    arXiv preprint arXiv:2410.06151 , 2024
    2024
    Citations: 4
  • Chapter 14-Federated sequential decision making: Bayesian optimization, reinforcement learning, and beyond
    Z Dai, FX Fan, C Tan, TN Hoang, BKH Low, P Jaillet
    Federated Learning. Academic Press , 2024
    2024
    Citations: 3
  • Information fidelity in tool-using llm agents: A martingale analysis of the model context protocol
    FX Fan, C Tan, R Wattenhofer, YS Ong
    arXiv preprint arXiv:2602.13320 , 2026
    2026
    Citations: 2
  • Unveiling and Mitigating Untargeted Poisoning Attacks on Federated Knowledge Graph Embedding
    W Jiang, K Liang, W Huang, X Zhang, Z Xu, G Wan, C Tan, FX Fan, ...
    Proceedings of the ACM Web Conference 2026, 2569-2580 , 2026
    2026
  • Why Do We Suffer for Fun? Ordeal Pleasure in Souls-like Games
    FX Fan
    arXiv preprint arXiv:2603.26677 , 2026
    2026
  • Provably Reliable Tool-Using LLM Agents: Formal Guarantees on Error Accumulation in the Model Context Protocol (MCP)
    FX Fan, C Tan, R Wattenhofer, YS Ong
    2026