Bangqi Pan — accepted AI-conference papers

2026

FedVeer: Self-Adaptive Skew Estimation for Robust Federated Learning

Yun Xin, Bangqi Pan, Jianfeng Lu, Shuqin Cao, Gang Li, Guanghui Wen

ICML 2026poster

Federated Learning (FL) enables collaborative model training across decentralized clients, but its performance often degrades under non-IID data distributions, particularly in the presence of data skew. Existing approaches mitigate this issue by estimating client skew via kernel density estimation o…

Cited by 0 Source ↗Scholar ↗

2026

OPTION: An Online Pricing Strategy for Asynchronous Federated Learning Against Free-Riding Attacks

Bangqi Pan, Jianfeng Lu, Shuqin Cao, Xiao Zhang, Gang Li, Guanghui Wen

AAAI 2026technical

Asynchronous Federated Learning (AFL) is acclaimed for accelerating collaborative training on heterogeneous systems by eliminating the wait for stragglers. While current solutions focus on improving convergence amidst update delays, they neglect how delayed aggregation fosters free-riding attacks, a

Cited by 0 Source ↗PDF ↗Scholar ↗