NeurIPS 2025 "data heterogeneity" Papers

Efficient Federated Learning against Byzantine Attacks and Data Heterogeneity via Aggregating Normalized Gradients

Shiyuan Zuo, Xingrun Yan, Rongfei Fan et al.

FedGPS: Statistical Rectification Against Data Heterogeneity in Federated Learning

Zhiqin Yang, Yonggang Zhang, Chenxin Li et al.

Unveiling the Power of Multiple Gossip Steps: A Stability-Based Generalization Analysis in Decentralized Training