mlsanityData to 14 Oct 2026

A Unified Convergence Analysis for Semi-Decentralized Learning: Sampled-to-Sampled vs. Sampled-to-All Communication

arXiv 2511.11560 ↗First posted 14 Nov 2025cs.LG cs.AI cs.DCcited by 0

Not on the map. Why?

Abstract (arXiv)

In semi-decentralized federated learning, devices primarily rely on device-to-device communication but occasionally interact with a central server. Periodically, a sampled subset of devices uploads their local models to the server, which computes an aggregate model. The server can then either (i) share this aggregate model only with the sampled clients (sampled-to-sampled, S2S) or (ii) broadcast it to all clients (sampled-to-all, S2A). Despite their practical significance, a rigorous theoretical and empirical comparison of these two strategies remains absent. We address this gap by analyzing S2S and S2A within a unified convergence framework that accounts for key system parameters: sampling rate, server aggregation frequency, and network connectivity. Our results, both analytical and experimental, reveal distinct regimes where one strategy outperforms the other, depending primarily on the degree of data heterogeneity across devices. These insights lead to concrete design guidelines for practical semi-decentralized FL deployments.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 22 of its 33 references that are in the map. First posted on arXiv 14 Nov 2025.

Builds on

22 of 33 references.

References · 22

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2019Advances and Open Problems in Federated Learningcited by 3,046
  3. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,475
  4. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,229
  5. 2020Adaptive Federated Optimizationcited by 1,046
  6. 2019Towards Federated Learning at Scale: System Designcited by 832
  7. 2018Local SGD Converges Fast and Communicates Littlecited by 605
  8. 2014Convex Optimization: Algorithms and Complexitycited by 575
  9. 2020Federated Learning with Matched Averagingcited by 564
  10. 2017Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descentcited by 502
  11. 2020A Unified Theory of Decentralized SGD with Changing Topology and Local Updatescited by 367
  12. 2013On the Convergence of Decentralized Gradient Descentcited by 159
10 more
  1. 2022ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally!cited by 134
  2. 2013Communication Efficient Distributed Optimization using an Approximate Newton-type Methodcited by 132
  3. 2021Semi-Decentralized Federated Learning with Cooperative D2D Local Model Aggregationscited by 51
  4. 2020Decentralized gradient methods: does topology matter?cited by 35
  5. 2014Stochastic Gradient-Push for Strongly Convex Functions on Time-Varying Directed Graphscited by 32
  6. 2022Refined Convergence and Topology Learning for Decentralized SGD with Heterogeneous Datacited by 32
  7. 2018New Convergence Aspects of Stochastic Gradient Algorithmscited by 30
  8. 2021Accelerating Gossip SGD with Periodic Global Averagingcited by 25
  9. 2025Unified Analysis of Decentralized Gradient Descent: a Contraction Mapping Frameworkcited by 10
  10. 2023Taming Subnet-Drift in D2D-Enabled Fog Learning: A Hierarchical Gradient Tracking Approachcited by 5

Built on by

Not cited yet.