mlsanityData to 14 Oct 2026

Deep Unfolding-based Weighted Averaging for Federated Learning in Heterogeneous Environments

arXiv 2212.12191 ↗First posted 23 Dec 2022cs.LG eess.SPcited by 0

Not on the map. Why?

Abstract (arXiv)

Federated learning is a collaborative model training method that iterates model updates by multiple clients and aggregation of the updates by a central server. Device and statistical heterogeneity of participating clients cause significant performance degradation so that an appropriate aggregation weight should be assigned to each client in the aggregation phase of the server. To adjust the aggregation weights, this paper employs deep unfolding, which is known as the parameter tuning method that leverages both learning capability using training data like deep learning and domain knowledge. This enables us to directly incorporate the heterogeneity of the environment of interest into the tuning of the aggregation weights. The proposed approach can be combined with various federated learning algorithms. The results of numerical experiments indicate that a higher test accuracy for unknown class-balanced data can be obtained with the proposed method than that with conventional heuristic weighting methods. The proposed method can handle large-scale learning models with the aid of pretrained models such that it can perform practical real-world tasks. Convergence rate of federated learning algorithms with the proposed method is also provided in this paper.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 39 of its 61 references that are in the map. First posted on arXiv 23 Dec 2022.

Builds on

39 of 61 references.

References · 39

  1. 2017Attention Is All You Needcited by 60,361
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  4. 2019Advances and Open Problems in Federated Learningcited by 3,046
  5. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  6. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
  7. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,229
  8. 2016Optimization Methods for Large-Scale Machine Learningcited by 1,150
  9. 2018Federated Learning with Non-IID Datacited by 1,108
  10. 2020Adaptive Federated Optimizationcited by 1,046
  11. 2020Meta-Learning in Neural Networks: A Surveycited by 950
  12. 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 906
27 more
  1. 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 851
  2. 2020Ensemble Distillation for Robust Model Fusion in Federated Learningcited by 682
  3. 2018Learning to Reweight Examples for Robust Deep Learningcited by 675
  4. 2018Local SGD Converges Fast and Communicates Littlecited by 605
  5. 2019Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraintscited by 503
  6. 2021Towards Personalized Federated Learningcited by 464
  7. 2019Agnostic Federated Learningcited by 456
  8. 2019Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processingcited by 421
  9. 2019Fair Resource Allocation in Federated Learningcited by 394
  10. 2019Bayesian Nonparametric Federated Learning of Neural Networkscited by 387
  11. 2021Federated Learning on Non-IID Data: A Surveycited by 346
  12. 2020Personalized Cross-Silo Federated Learning on Non-IID Datacited by 283
  13. 2019Improving Federated Learning Personalization via Model Agnostic Meta Learningcited by 269
  14. 2020Federated learning with hierarchical clustering of local updates to improve training on non-IID datacited by 223
  15. 2020Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategiescited by 198
  16. 2022Federated Learning from Pre-Trained Models: A Contrastive Learning Approachcited by 142
  17. 2020Model-Based Deep Learningcited by 141
  18. 2020Optimal Client Sampling for Federated Learningcited by 124
  19. 2019Communication-Efficient Federated Deep Learning with Asynchronous Model Update and Temporally Weighted Aggregationcited by 100
  20. 2019MATCHA: Speeding Up Decentralized SGD via Matching Decomposition Samplingcited by 67
  21. 2020Fast-Convergent Federated Learning with Adaptive Weightingcited by 67
  22. 2020Personalized Federated Learning for Intelligent IoT Applications: A Cloud-Edge based Frameworkcited by 59
  23. 2021Federated Learning: A Signal Processing Perspectivecited by 49
  24. 2020Communication-Efficient Federated Learning via Optimal Client Samplingcited by 39
  25. 2020FOCUS: Dealing with Label Quality Disparity in Federated Learningcited by 36
  26. 2021Graph Signal Restoration Using Nested Deep Algorithm Unrollingcited by 13
  27. 2019Deep Learning-Based Average Consensuscited by 2

Built on by

Not cited yet.