# Federated Learning at the Network Edge: When Not All Nodes are Created Equal

arXiv: https://arxiv.org/abs/2101.01995 · HTML: https://mlsanity.com/paper/2101.01995/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jan 2021.

## Built on by (most cited first, 10 of 10)

- [Decentralized Federated Learning: A Survey and Perspective](https://mlsanity.com/paper/2306.01603/) (2023)
- [Machine Learning for Large-Scale Optimization in 6G Wireless Networks](https://mlsanity.com/paper/2301.03377/) (2023)
- [Matching DNN Compression and Cooperative Training with Resources and Data Availability](https://mlsanity.com/paper/2212.02304/) (2022)
- [Federated Learning for 6G: Paradigms, Taxonomy, Recent Advances and Insights](https://mlsanity.com/paper/2312.04688/) (2023)
- [Dynamic Scheduling for Federated Edge Learning with Streaming Data](https://mlsanity.com/paper/2305.01238/) (2023)
- [Flexible Parallel Learning in Edge Scenarios: Communication, Computational and Energy Cost](https://mlsanity.com/paper/2201.07402/) (2022)
- [Context-Aware Orchestration of Energy-Efficient Gossip Learning Schemes](https://mlsanity.com/paper/2404.12023/) (2024)
- [Unexpectedly Useful: Convergence Bounds And Real-World Distributed Learning](https://mlsanity.com/paper/2212.02155/) (2022)
- [Decentralized Health Intelligence Network (DHIN)](https://mlsanity.com/paper/2408.06240/) (2024)
- [DFCA: Decentralized Federated Clustering Algorithm](https://mlsanity.com/paper/2510.15300/) (2025)

## Abstract (arXiv)

Under the federated learning paradigm, a set of nodes can cooperatively train a machine learning model with the help of a centralized server. Such a server is also tasked with assigning a weight to the information received from each node, and often also to drop too-slow nodes from the learning process. Both decisions have major impact on the resulting learning performance, and can interfere with each other in counterintuitive ways. In this paper, we focus on edge networking scenarios and investigate existing and novel approaches to such model-weighting and node-dropping decisions. Leveraging a set of real-world experiments, we find that popular, straightforward decision-making approaches may yield poor performance, and that considering the quality of data in addition to its quantity can substantially improve learning.