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

arXiv: https://arxiv.org/abs/2405.00579 · HTML: https://mlsanity.com/paper/2405.00579/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 May 2024.

## Built on by (most cited first, 2 of 2)

- [Benchmarking Data Heterogeneity Evaluation Approaches for Personalized Federated Learning](https://mlsanity.com/paper/2410.07286/) (2024)
- [ELSA: Efficient LLM-Centric Split Aggregation for Privacy-Aware Hierarchical Federated Learning over the Network Edge](https://mlsanity.com/paper/2601.13824/) (2026)

## Abstract (arXiv)

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.