mlsanityData to 7 Oct 2026

Optimisation of federated learning settings under statistical heterogeneity variations

arXiv 2406.06340 ↗First posted 10 Jun 2024cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) enables local devices to collaboratively learn a shared predictive model by only periodically sharing model parameters with a central aggregator. However, FL can be disadvantaged by statistical heterogeneity produced by the diversity in each local devices data distribution, which creates different levels of Independent and Identically Distributed (IID) data. Furthermore, this can be more complex when optimising different combinations of FL parameters and choosing optimal aggregation. In this paper, we present an empirical analysis of different FL training parameters and aggregators over various levels of statistical heterogeneity on three datasets. We propose a systematic data partition strategy to simulate different levels of statistical heterogeneity and a metric to measure the level of IID. Additionally, we empirically identify the best FL model and key parameters for datasets of different characteristics. On the basis of these, we present recommended guidelines for FL parameters and aggregators to optimise model performance under different levels of IID and with different datasets

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 23 of its 36 references that are in the map. First posted on arXiv 10 Jun 2024.

Builds on

23 of 36 references.

References · 23

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  3. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  4. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
  5. 2018Federated Learning with Non-IID Datacited by 1,099
  6. 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 836
  7. 2021Federated Learning on Non-IID Data Silos: An Experimental Studycited by 566
  8. 2020Federated Learning with Matched Averagingcited by 564
  9. 2019Federated Learning with Personalization Layerscited by 533
  10. 2021Federated Learning on Non-IID Data: A Surveycited by 345
  11. 2019Improving Federated Learning Personalization via Model Agnostic Meta Learningcited by 264
  12. 2020Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategiescited by 196
11 more
  1. 2019SCAFFOLD: Stochastic Controlled Averaging for Federated Learningcited by 174
  2. 2023Heterogeneous Federated Learning: State-of-the-art and Research Challengescited by 160
  3. 2021Rethinking Architecture Design for Tackling Data Heterogeneity in Federated Learningcited by 111
  4. 2022Federated Learning with Label Distribution Skew via Logits Calibrationcited by 108
  5. 2020From Federated Learning to Federated Neural Architecture Search: A Surveycited by 42
  6. 2020A Secure Federated Learning Framework for 5G Networkscited by 32
  7. 2020Federated Learning and Wireless Communicationscited by 27
  8. 2022Rethinking Data Heterogeneity in Federated Learning: Introducing a New Notion and Standard Benchmarkscited by 24
  9. 2021DeepFace-EMD: Re-ranking Using Patch-wise Earth Mover's Distance Improves Out-Of-Distribution Face Identificationcited by 20
  10. 2021Federated Learning Versus Classical Machine Learning: A Convergence Comparisoncited by 7
  11. 2020Federated Multi-Mini-Batch: An Efficient Training Approach to Federated Learning in Non-IID Environmentscited by 3

Built on by

Not cited yet.