# Enhancing Convergence in Federated Learning: A Contribution-Aware Asynchronous Approach

arXiv: https://arxiv.org/abs/2402.10991 · HTML: https://mlsanity.com/paper/2402.10991/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 31 references that are in the map.
- First posted on arXiv 16 Feb 2024.

## Builds on (most cited first, 6 of 6)

- [Particle Filter SLAM for Vehicle Localization](https://mlsanity.com/paper/2402.07429/) (2024)
- [News Recommendation with Attention Mechanism](https://mlsanity.com/paper/2402.07422/) (2024)
- [Financial Time-Series Forecasting: Towards Synergizing Performance And Interpretability Within a Hybrid Machine Learning Approach](https://mlsanity.com/paper/2401.00534/) (2023)
- [Federated Learning with Instance-Dependent Noisy Label](https://mlsanity.com/paper/2312.10324/) (2023)
- [CAFE: Carbon-Aware Federated Learning in Geographically Distributed Data Centers](https://mlsanity.com/paper/2311.03615/) (2023)
- [Joint Client Assignment and UAV Route Planning for Indirect-Communication Federated Learning](https://mlsanity.com/paper/2304.10744/) (2023)

## Built on by (most cited first, 1 of 1)

- [Heterogeneity-aware Personalized Federated Learning via Adaptive Dual-Agent Reinforcement Learning](https://mlsanity.com/paper/2501.16966/) (2025)

## Abstract (arXiv)

Federated Learning (FL) is a distributed machine learning paradigm that allows clients to train models on their data while preserving their privacy. FL algorithms, such as Federated Averaging (FedAvg) and its variants, have been shown to converge well in many scenarios. However, these methods require clients to upload their local updates to the server in a synchronous manner, which can be slow and unreliable in realistic FL settings. To address this issue, researchers have developed asynchronous FL methods that allow clients to continue training on their local data using a stale global model. However, most of these methods simply aggregate all of the received updates without considering their relative contributions, which can slow down convergence. In this paper, we propose a contribution-aware asynchronous FL method that takes into account the staleness and statistical heterogeneity of the received updates. Our method dynamically adjusts the contribution of each update based on these factors, which can speed up convergence compared to existing methods.