# Accurate and Fast Federated Learning via IID and Communication-Aware Grouping

arXiv: https://arxiv.org/abs/2012.04857 · HTML: https://mlsanity.com/paper/2012.04857/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Dec 2020.

## Built on by (most cited first, 6 of 6)

- [Optimality and Stability in Federated Learning: A Game-theoretic Approach](https://mlsanity.com/paper/2106.09580/) (2021)
- [HiFlash: Communication-Efficient Hierarchical Federated Learning with Adaptive Staleness Control and Heterogeneity-aware Client-Edge Association](https://mlsanity.com/paper/2301.06447/) (2023)
- [Energy-Aware Edge Association for Cluster-based Personalized Federated Learning](https://mlsanity.com/paper/2202.02727/) (2022)
- [Resource-Efficient Federated Fine-Tuning Large Language Models for Heterogeneous Data](https://mlsanity.com/paper/2503.21213/) (2025)
- [IMFL-AIGC: Incentive Mechanism Design for Federated Learning Empowered by Artificial Intelligence Generated Content](https://mlsanity.com/paper/2406.08526/) (2024)
- [Dual-Segment Clustering Strategy for Hierarchical Federated Learning in Heterogeneous Wireless Environments](https://mlsanity.com/paper/2405.09276/) (2024)

## Abstract (arXiv)

Federated learning has emerged as a new paradigm of collaborative machine learning; however, it has also faced several challenges such as non-independent and identically distributed(IID) data and high communication cost. To this end, we propose a novel framework of IID and communication-aware group federated learning that simultaneously maximizes both accuracy and communication speed by grouping nodes based on data distributions and physical locations of the nodes. Furthermore, we provide a formal convergence analysis and an efficient optimization algorithm called FedAvg-IC. Experimental results show that, compared with the state-of-the-art algorithms, FedAvg-IC improved the test accuracy by up to 22.2% and simultaneously reduced the communication time to as small as 12%.