LEAP: Optimization Hierarchical Federated Learning on Non-IID Data with Coalition Formation Game

LEAP: Optimization Hierarchical Federated Learning on Non-IID Data with Coalition Formation Game

Jianfeng Lu, Yue Chen, Shuqin Cao, Longbiao Chen, Wei Wang, Yun Xin

Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence
Main Track. Pages 4660-4668. https://doi.org/10.24963/ijcai.2024/515

Although Hierarchical Federated Learning (HFL) utilizes edge servers (ESs) to alleviate communication burdens, its model performance will be degraded by non-IID data and limited communication resources. Current works often assume that data is uniformly distributed, which however contradicts the heterogeneity of IoT. Solutions involving additional model training to check the data distribution inevitably increase computational costs and the risk of privacy leakage. The challenges in solving these issues are how to reduce the impact of non-IID data without involving raw data, and how to rationalize the communication resource allocation for addressing straggler problem. To tackle these challenges, we propose a novel optimization method based on coaLition formation gamE and grAdient Projection, called LEAP. Specifically, we combine edge data distribution with coalition formation game innovatively to adjust the correlations between clients and ESs dynamically, ensuring optimal correlations. We further capture the client heterogeneity to achieve the rational bandwidth allocation from coalition perception and determine the optimal transmission power within specified delay constraints at the client level. Experimental results on four real datasets show that LEAP is able to achieve 20.62% improvement in model accuracy compared to the state-of-the-art baselines. Moreover, LEAP effectively reduces transmission energy consumption by at least about 2.24 times.
Keywords:
Machine Learning: ML: Evaluation
Agent-based and Multi-agent Systems: MAS: Resource allocation
Game Theory and Economic Paradigms: GTEP: Mechanism design
Machine Learning: ML: Game Theory