Proceedings

Harmonizing Federated Heterogeneous Optimization via Adaptive Objective Rectification

Jianrong Lu, Bangwei Li, Zhuoya Gu, Peng Fang, Ziming Zhao, Jianhai Chen

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Main Track. Pages 3961-3969.

https://doi.org/10.24963/ijcai.2026/441

Keywords

  • Machine Learning: Optimization
  • Knowledge Representation and Reasoning: Applications
  • Machine Learning: Federated learning

Abstract

Federated optimization under data heterogeneity presents a significant challenge, often leading to suboptimal model performance. While numerous methods aim to replicate the ideal performance of centralized training, they frequently fall short in highly heterogeneous settings. In this paper, we introduce HaFedHo, an adaptive objective rectification method that harmonizes local training with the ideal data-centralized objective, requiring minimal modifications to the standard federated learning framework. HaFedHo operates by first decoupling the centralized objective and then employing a dynamic Taylor series expansion to accurately estimate the global objective for each client. Our theoretical analysis shows that the estimation error provably converges to zero as training progresses. Furthermore, extensive experiments on real-world datasets demonstrate that HaFedHo surpasses state-of-the-art methods, including SCAFFOLD, MimeLite, and FedDyn, in both test accuracy and communication efficiency. Notably, HaFedHo maintains its superior performance even with a client participation rate as low as $0.2\%$ in severely heterogeneous environments.

jianrong Lu, Bangwei Li, Zhuoya Gu, Peng Fang, Ziming Zhao, and Jianhai Chen. 2026. Harmonizing Federated Heterogeneous Optimization via Adaptive Objective Rectification. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 3961–3969. https://doi.org/10.24963/ijcai.2026/441
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards