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

TL;DR

LEAP introduces a coalition formation game-based optimization approach for hierarchical federated learning, effectively addressing non-IID data challenges and resource allocation to improve model accuracy and reduce energy consumption.

Contribution

It proposes a novel coalition formation game and gradient projection method to dynamically optimize client-ES correlations and resource allocation in HFL with non-IID data.

Findings

Achieves 20.62% improvement in model accuracy over baselines.

Reduces transmission energy consumption by at least 2.24 times.

Effectively handles non-IID data and resource constraints in HFL.

Abstract

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 of additional model training to check the data distribution inevitably increases 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, which ensures 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 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 reduce transmission energy consumption by at least about 2.24 times.