# Federated Learning with Communication Delay in Edge Networks

arXiv: https://arxiv.org/abs/2008.09323 · HTML: https://mlsanity.com/paper/2008.09323/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Aug 2020.

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

- [Semi-Decentralized Federated Learning with Cooperative D2D Local Model Aggregations](https://mlsanity.com/paper/2103.10481/) (2021)
- [Delay-Aware Hierarchical Federated Learning](https://mlsanity.com/paper/2303.12414/) (2023)
- [Loss Tolerant Federated Learning](https://mlsanity.com/paper/2105.03591/) (2021)
- [Resource-Efficient and Delay-Aware Federated Learning Design under Edge Heterogeneity](https://mlsanity.com/paper/2112.13926/) (2021)
- [Federated Learning Beyond the Star: Local D2D Model Consensus with Global Cluster Sampling](https://mlsanity.com/paper/2109.03350/) (2021)
- [Importance-Aware Feature Sparsification for Wireless Split Learning](https://mlsanity.com/paper/2609.39194/) (2026)

## Abstract (arXiv)

Federated learning has received significant attention as a potential solution for distributing machine learning (ML) model training through edge networks. This work addresses an important consideration of federated learning at the network edge: communication delays between the edge nodes and the aggregator. A technique called FedDelAvg (federated delayed averaging) is developed, which generalizes the standard federated averaging algorithm to incorporate a weighting between the current local model and the delayed global model received at each device during the synchronization step. Through theoretical analysis, an upper bound is derived on the global model loss achieved by FedDelAvg, which reveals a strong dependency of learning performance on the values of the weighting and learning rate. Experimental results on a popular ML task indicate significant improvements in terms of convergence speed when optimizing the weighting scheme to account for delays.