mlsanityData to 13 Oct 2026

FLAGS Framework for Comparative Analysis of Federated Learning Algorithms

arXiv 2212.07179 ↗First posted 14 Dec 2022cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) has become a key choice for distributed machine learning. Initially focused on centralized aggregation, recent works in FL have emphasized greater decentralization to adapt to the highly heterogeneous network edge. Among these, Hierarchical, Device-to-Device and Gossip Federated Learning (HFL, D2DFL & GFL respectively) can be considered as foundational FL algorithms employing fundamental aggregation strategies. A number of FL algorithms were subsequently proposed employing multiple fundamental aggregation schemes jointly. Existing research, however, subjects the FL algorithms to varied conditions and gauges the performance of these algorithms mainly against Federated Averaging (FedAvg) only. This work consolidates the FL landscape and offers an objective analysis of the major FL algorithms through a comprehensive cross-evaluation for a wide range of operating conditions. In addition to the three foundational FL algorithms, this work also analyzes six derived algorithms. To enable a uniform assessment, a multi-FL framework named FLAGS: Federated Learning AlGorithms Simulation has been developed for rapid configuration of multiple FL algorithms. Our experiments indicate that fully decentralized FL algorithms achieve comparable accuracy under multiple operating conditions, including asynchronous aggregation and the presence of stragglers. Furthermore, decentralized FL can also operate in noisy environments and with a comparably higher local update rate. However, the impact of extremely skewed data distributions on decentralized FL is much more adverse than on centralized variants. The results indicate that it may not be necessary to restrict the devices to a single FL algorithm; rather, multi-FL nodes may operate with greater efficiency.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 18 of its 37 references that are in the map. First posted on arXiv 14 Dec 2022.

Builds on

18 of 37 references.

References · 18

  1. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,328
  2. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,470
  3. 2018LEAF: A Benchmark for Federated Settingscited by 789
  4. 2021Model-Contrastive Federated Learningcited by 766
  5. 2021Federated Learning on Non-IID Data Silos: An Experimental Studycited by 568
  6. 2020Flower: A Friendly Federated Learning Research Frameworkcited by 453
  7. 2020FedML: A Research Library and Benchmark for Federated Machine Learningcited by 300
  8. 2019Client-Edge-Cloud Hierarchical Federated Learningcited by 202
  9. 2021FedScale: Benchmarking Model and System Performance of Federated Learning at Scalecited by 136
  10. 2019One-Shot Federated Learningcited by 125
  11. 2019Convergence of Edge Computing and Deep Learning: A Comprehensive Surveycited by 120
  12. 2019Hierarchical Federated Learning Across Heterogeneous Cellular Networkscited by 98
6 more
  1. 2019Federated Learning with Cooperating Devices: A Consensus Approach for Massive IoT Networkscited by 79
  2. 2019Detailed comparison of communication efficiency of split learning and federated learningcited by 77
  3. 2021Federated Learning over Wireless Device-to-Device Networks: Algorithms and Convergence Analysiscited by 51
  4. 2021Semi-Decentralized Federated Learning with Cooperative D2D Local Model Aggregationscited by 51
  5. 2020Decentralized Federated Learning via Mutual Knowledge Transfercited by 43
  6. 2018GossipGraD: Scalable Deep Learning using Gossip Communication based Asynchronous Gradient Descentcited by 19

Built on by

Not cited yet.