# Robustness of Decentralised Learning to Nodes and Data Disruption

arXiv: https://arxiv.org/abs/2405.02377 · HTML: https://mlsanity.com/paper/2405.02377/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 27 references that are in the map.
- First posted on arXiv 3 May 2024.

## Builds on (most cited first, 12 of 12)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [A Unified Theory of Decentralized SGD with Changing Topology and Local Updates](https://mlsanity.com/paper/2003.10422/) (2020)
- [Asynchronous Federated Optimization](https://mlsanity.com/paper/1903.03934/) (2019)
- [Cooperative Game Theory Approaches for Network Partitioning](https://mlsanity.com/paper/1707.03587/) (2017)
- [Decentralized Federated Averaging](https://mlsanity.com/paper/2104.11375/) (2021)
- [Federated Learning with Cooperating Devices: A Consensus Approach for Massive IoT Networks](https://mlsanity.com/paper/1912.13163/) (2019)
- [Topology-aware Generalization of Decentralized SGD](https://mlsanity.com/paper/2206.12680/) (2022)
- [The effect of network topologies on fully decentralized learning: a preliminary investigation](https://mlsanity.com/paper/2307.15947/) (2023)
- [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)
- [Exploring the Impact of Disrupted Peer-to-Peer Communications on Fully Decentralized Learning in Disaster Scenarios](https://mlsanity.com/paper/2310.02986/) (2023)

## Built on by (most cited first, 5 of 5)

- [Self-Regulating Random Walks for Resilient Decentralized Learning on Graphs](https://mlsanity.com/paper/2407.11762/) (2024)
- [Self-Creating Random Walks for Decentralized Learning under Pac-Man Attacks](https://mlsanity.com/paper/2601.07674/) (2026)
- [The Built-In Robustness of Decentralized Federated Averaging to Bad Data](https://mlsanity.com/paper/2502.18097/) (2025)
- [Operating Regimes of Decentralized Learning Under Mobility and Bandwidth Constraints](https://mlsanity.com/paper/2606.28342/) (2026)
- [Decentralised Federated Learning over Temporal Networks: The Role of Heterogeneities](https://mlsanity.com/paper/2607.03171/) (2026)

## Abstract (arXiv)

In the vibrant landscape of AI research, decentralised learning is gaining momentum. Decentralised learning allows individual nodes to keep data locally where they are generated and to share knowledge extracted from local data among themselves through an interactive process of collaborative refinement. This paradigm supports scenarios where data cannot leave local nodes due to privacy or sovereignty reasons or real-time constraints imposing proximity of models to locations where inference has to be carried out. The distributed nature of decentralised learning implies significant new research challenges with respect to centralised learning. Among them, in this paper, we focus on robustness issues. Specifically, we study the effect of nodes' disruption on the collective learning process. Assuming a given percentage of "central" nodes disappear from the network, we focus on different cases, characterised by (i) different distributions of data across nodes and (ii) different times when disruption occurs with respect to the start of the collaborative learning task. Through these configurations, we are able to show the non-trivial interplay between the properties of the network connecting nodes, the persistence of knowledge acquired collectively before disruption or lack thereof, and the effect of data availability pre- and post-disruption. Our results show that decentralised learning processes are remarkably robust to network disruption. As long as even minimum amounts of data remain available somewhere in the network, the learning process is able to recover from disruptions and achieve significant classification accuracy. This clearly varies depending on the remaining connectivity after disruption, but we show that even nodes that remain completely isolated can retain significant knowledge acquired before the disruption.