mlsanityData to 14 Oct 2026

An Enhanced Federated Prototype Learning Method under Domain Shift

arXiv 2409.18578 ↗First posted 27 Sep 2024cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) allows collaborative machine learning training without sharing private data. Numerous studies have shown that one significant factor affecting the performance of federated learning models is the heterogeneity of data across different clients, especially when the data is sampled from various domains. A recent paper introduces variance-aware dual-level prototype clustering and uses a novel α-sparsity prototype loss, which increases intra-class similarity and reduces inter-class similarity. To ensure that the features converge within specific clusters, we introduce an improved algorithm, Federated Prototype Learning with Convergent Clusters, abbreviated as FedPLCC. To increase inter-class distances, we weight each prototype with the size of the cluster it represents. To reduce intra-class distances, considering that prototypes with larger distances might come from different domains, we select only a certain proportion of prototypes for the loss function calculation. Evaluations on the Digit-5, Office-10, and DomainNet datasets show that our method performs better than existing approaches.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 28 of its 33 references that are in the map. First posted on arXiv 27 Sep 2024.

Builds on

28 of 33 references.

References · 28

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  3. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  4. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  5. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  6. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,331
  7. 2018Federated Learning with Non-IID Datacited by 1,108
  8. 2021Model-Contrastive Federated Learningcited by 766
  9. 2021Federated Learning Based on Dynamic Regularizationcited by 562
  10. 2020Understanding the Behaviour of Contrastive Losscited by 398
  11. 2021FedProto: Federated Prototype Learning across Heterogeneous Clientscited by 352
  12. 2021Federated Learning on Non-IID Data: A Surveycited by 346
16 more
  1. 2020Learning to Generate Novel Domains for Domain Generalizationcited by 296
  2. 2021No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Datacited by 241
  3. 2021FedBABU: Towards Enhanced Representation for Federated Image Classificationcited by 182
  4. 2022Federated Learning from Pre-Trained Models: A Contrastive Learning Approachcited by 142
  5. 2021Local Learning Matters: Rethinking Data Heterogeneity in Federated Learningcited by 114
  6. 2019Efficient Parameter-free Clustering Using First Neighbor Relationscited by 97
  7. 2019Hyperspherical Prototype Networkscited by 86
  8. 2021FedProc: Prototypical Contrastive Federated Learning on Non-IID datacited by 81
  9. 2022Tackling Data Heterogeneity in Federated Learning with Class Prototypescited by 67
  10. 2022Federated Learning on Heterogeneous and Long-Tailed Data via Classifier Re-Training with Federated Featurescited by 63
  11. 2021A Prototype-Oriented Framework for Unsupervised Domain Adaptationcited by 62
  12. 2022FedFA: Federated Learning with Feature Anchors to Align Features and Classifiers for Heterogeneous Datacited by 50
  13. 2022HCSC: Hierarchical Contrastive Selective Codingcited by 43
  14. 2023Generalizable Heterogeneous Federated Cross-Correlation and Instance Similarity Learningcited by 40
  15. 2024Taming Cross-Domain Representation Variance in Federated Prototype Learning with Heterogeneous Data Domainscited by 28
  16. 2015Prototypical Priors: From Improving Classification to Zero-Shot Learningcited by 14

Built on by

Not cited yet.