# Decentralised Resource Sharing in TinyML: Wireless Bilayer Gossip Parallel SGD for Collaborative Learning

arXiv: https://arxiv.org/abs/2501.04817 · HTML: https://mlsanity.com/paper/2501.04817/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 40 references that are in the map.
- First posted on arXiv 8 Jan 2025.

## Builds on (most cited first, 18 of 18)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Federated Learning: Challenges, Methods, and Future Directions](https://mlsanity.com/paper/1908.07873/) (2019)
- [Federated Learning with Non-IID Data](https://mlsanity.com/paper/1806.00582/) (2018)
- [Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraints](https://mlsanity.com/paper/1910.01991/) (2019)
- [Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent](https://mlsanity.com/paper/1705.09056/) (2017)
- [Adaptive Federated Learning in Resource Constrained Edge Computing Systems](https://mlsanity.com/paper/1804.05271/) (2018)
- [Federated Learning on Non-IID Data: A Survey](https://mlsanity.com/paper/2106.06843/) (2021)
- [MCUNet: Tiny Deep Learning on IoT Devices](https://mlsanity.com/paper/2007.10319/) (2020)
- [Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication](https://mlsanity.com/paper/1902.00340/) (2019)
- [On-Device Training Under 256KB Memory](https://mlsanity.com/paper/2206.15472/) (2022)
- [Asynchronous Decentralized Parallel Stochastic Gradient Descent](https://mlsanity.com/paper/1710.06952/) (2017)
- [Decentralized Federated Learning: Fundamentals, State of the Art, Frameworks, Trends, and Challenges](https://mlsanity.com/paper/2211.08413/) (2022)
- [Decentralized Federated Learning: A Survey and Perspective](https://mlsanity.com/paper/2306.01603/) (2023)
- [A Survey on Decentralized Federated Learning](https://mlsanity.com/paper/2308.04604/) (2023)
- [Topology-aware Federated Learning in Edge Computing: A Comprehensive Survey](https://mlsanity.com/paper/2302.02573/) (2023)
- [Over-the-Air Decentralized Federated Learning](https://mlsanity.com/paper/2106.08011/) (2021)
- [On the Convergence of Decentralized Federated Learning Under Imperfect Information Sharing](https://mlsanity.com/paper/2303.10695/) (2023)
- [Efficient Neural Networks for Tiny Machine Learning: A Comprehensive Review](https://mlsanity.com/paper/2311.11883/) (2023)

## Built on by (most cited first, 2 of 2)

- [MambaLiteSR: Image Super-Resolution with Low-Rank Mamba using Knowledge Distillation](https://mlsanity.com/paper/2502.14090/) (2025)
- [A Multicore and Edge TPU-Accelerated Multimodal TinyML System for Livestock Behavior Recognition](https://mlsanity.com/paper/2504.11467/) (2025)

## Abstract (arXiv)

With the growing computational capabilities of microcontroller units (MCUs), edge devices can now support machine learning models. However, deploying decentralised federated learning (DFL) on such devices presents key challenges, including intermittent connectivity, limited communication range, and dynamic network topologies. This paper proposes a novel framework, bilayer Gossip Decentralised Parallel Stochastic Gradient Descent (GD PSGD), designed to address these issues in resource-constrained environments. The framework incorporates a hierarchical communication structure using Distributed Kmeans (DKmeans) clustering for geographic grouping and a gossip protocol for efficient model aggregation across two layers: intra-cluster and inter-cluster. We evaluate the framework's performance against the Centralised Federated Learning (CFL) baseline using the MCUNet model on the CIFAR-10 dataset under IID and Non-IID conditions. Results demonstrate that the proposed method achieves comparable accuracy to CFL on IID datasets, requiring only 1.8 additional rounds for convergence. On Non-IID datasets, the accuracy loss remains under 8% for moderate data imbalance. These findings highlight the framework's potential to support scalable and privacy-preserving learning on edge devices with minimal performance trade-offs.