# Decentralised Federated Learning over Temporal Networks: The Role of Heterogeneities

arXiv: https://arxiv.org/abs/2607.03171 · HTML: https://mlsanity.com/paper/2607.03171/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 67 references that are in the map.
- First posted on arXiv 3 Jul 2026.

## Builds on (most cited first, 19 of 19)

- [Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent](https://mlsanity.com/paper/1705.09056/) (2017)
- [Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication](https://mlsanity.com/paper/1902.00340/) (2019)
- [D2: Decentralized Training over Decentralized Data](https://mlsanity.com/paper/1803.07068/) (2018)
- [Decentralized Federated Learning: Fundamentals, State of the Art, Frameworks, Trends, and Challenges](https://mlsanity.com/paper/2211.08413/) (2022)
- [Decentralized Federated Learning: A Segmented Gossip Approach](https://mlsanity.com/paper/1908.07782/) (2019)
- [Contact patterns among high school students](https://mlsanity.com/paper/1409.5318/) (2014)
- [Asynchronous Decentralized Learning over Unreliable Wireless Networks](https://mlsanity.com/paper/2202.00955/) (2022)
- [Privacy-preserving Decentralized Federated Learning over Time-varying Communication Graph](https://mlsanity.com/paper/2210.00325/) (2022)
- [Impact of network topology on the performance of Decentralized Federated Learning](https://mlsanity.com/paper/2402.18606/) (2024)
- [Coordination-free Decentralised Federated Learning on Complex Networks: Overcoming Heterogeneity](https://mlsanity.com/paper/2312.04504/) (2023)
- [Quantum Google in a Complex Network](https://mlsanity.com/paper/1303.3891/) (2013)
- [Directed Percolation in Temporal Networks](https://mlsanity.com/paper/2107.01510/) (2021)
- [Robustness of Decentralised Learning to Nodes and Data Disruption](https://mlsanity.com/paper/2405.02377/) (2024)
- [Time varying networks and the weakness of strong ties](https://mlsanity.com/paper/1303.5966/) (2013)
- [Decentralized Federated Learning with Gradient Tracking over Time-Varying Directed Networks](https://mlsanity.com/paper/2409.17189/) (2024)
- [Decentralized Federated Learning with Distributed Aggregation Weight Optimization](https://mlsanity.com/paper/2511.03284/) (2025)
- [Temporal networks: slowing down diffusion by long lasting interactions](https://mlsanity.com/paper/1305.2938/) (2013)
- [Directed Percolation in Random Temporal Network Models with Heterogeneities](https://mlsanity.com/paper/2110.07698/) (2021)
- [Time-varying Mixing Matrix Design for Energy-efficient Decentralized Federated Learning](https://mlsanity.com/paper/2512.24069/) (2025)

## Abstract (arXiv)

Decentralised federated learning, based on peer-to-peer communication, is increasingly proposed for on-device training of machine learning models, promising a privacy-preserving, communication-efficient training process with no risk of single-point failure. However, the role of structural and temporal inhomogeneities in such fully decentralised settings remains poorly understood. Here, we investigate their effects when model parameters are locally averaged during aggregation. We show that the decentralised federated learning process is governed, both in the early phase and the late, stationary limit, by the same dynamics as a lazy random-walk diffusion process on temporal networks. Based on this mapping, we demonstrate that the typical experimental scenario used in decentralised federated learning leads to unrealistically rapid convergence because of ignoring the temporal and structural inhomogeneities inherent in the communication network. We analyse real-world temporal networks and find that inhomogeneities most often dramatically slow down diffusion, hence the convergence process.