# Federated Learning Beyond the Star: Local D2D Model Consensus with Global Cluster Sampling

arXiv: https://arxiv.org/abs/2109.03350 · HTML: https://mlsanity.com/paper/2109.03350/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 19 references that are in the map.
- First posted on arXiv 7 Sep 2021.

## Builds on (most cited first, 13 of 13)

- [Federated Learning with Non-IID Data](https://mlsanity.com/paper/1806.00582/) (2018)
- [Convex Optimization: Algorithms and Complexity](https://mlsanity.com/paper/1405.4980/) (2014)
- [Adaptive Federated Learning in Resource Constrained Edge Computing Systems](https://mlsanity.com/paper/1804.05271/) (2018)
- [A Joint Learning and Communications Framework for Federated Learning over Wireless Networks](https://mlsanity.com/paper/1909.07972/) (2019)
- [Client-Edge-Cloud Hierarchical Federated Learning](https://mlsanity.com/paper/1905.06641/) (2019)
- [Federated Learning with Cooperating Devices: A Consensus Approach for Massive IoT Networks](https://mlsanity.com/paper/1912.13163/) (2019)
- [Semi-Decentralized Federated Learning with Cooperative D2D Local Model Aggregations](https://mlsanity.com/paper/2103.10481/) (2021)
- [Multi-Stage Hybrid Federated Learning over Large-Scale D2D-Enabled Fog Networks](https://mlsanity.com/paper/2007.09511/) (2020)
- [Hybrid-FL for Wireless Networks: Cooperative Learning Mechanism Using Non-IID Data](https://mlsanity.com/paper/1905.07210/) (2019)
- [Decentralized Federated Learning via SGD over Wireless D2D Networks](https://mlsanity.com/paper/2002.12507/) (2020)
- [Network-Aware Optimization of Distributed Learning for Fog Computing](https://mlsanity.com/paper/2004.08488/) (2020)
- [Federated Learning with Communication Delay in Edge Networks](https://mlsanity.com/paper/2008.09323/) (2020)
- [Energy Efficient Power and Channel Allocation in Underlay Device to Multi Device Communications](https://mlsanity.com/paper/1905.03089/) (2019)

## Abstract (arXiv)

Federated learning has emerged as a popular technique for distributing model training across the network edge. Its learning architecture is conventionally a star topology between the devices and a central server. In this paper, we propose two timescale hybrid federated learning (TT-HF), which migrates to a more distributed topology via device-to-device (D2D) communications. In TT-HF, local model training occurs at devices via successive gradient iterations, and the synchronization process occurs at two timescales: (i) macro-scale, where global aggregations are carried out via device-server interactions, and (ii) micro-scale, where local aggregations are carried out via D2D cooperative consensus formation in different device clusters. Our theoretical analysis reveals how device, cluster, and network-level parameters affect the convergence of TT-HF, and leads to a set of conditions under which a convergence rate of O(1/t) is guaranteed. Experimental results demonstrate the improvements in convergence and utilization that can be obtained by TT-HF over state-of-the-art federated learning baselines.