mlsanityData to 14 Oct 2026

Classifier Clustering and Feature Alignment for Federated Learning under Distributed Concept Drift

arXiv 2410.18478 ↗First posted 24 Oct 2024cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

Data heterogeneity is one of the key challenges in federated learning, and many efforts have been devoted to tackling this problem. However, distributed concept drift with data heterogeneity, where clients may additionally experience different concept drifts, is a largely unexplored area. In this work, we focus on real drift, where the conditional distribution P(Y|X) changes. We first study how distributed concept drift affects the model training and find that local classifier plays a critical role in drift adaptation. Moreover, to address data heterogeneity, we study the feature alignment under distributed concept drift, and find two factors that are crucial for feature alignment: the conditional distribution P(Y|X) and the degree of data heterogeneity. Motivated by the above findings, we propose FedCCFA, a federated learning framework with classifier clustering and feature alignment. To enhance collaboration under distributed concept drift, FedCCFA clusters local classifiers at class-level and generates clustered feature anchors according to the clustering results. Assisted by these anchors, FedCCFA adaptively aligns clients' feature spaces based on the entropy of label distribution P(Y), alleviating the inconsistency in feature space. Our results demonstrate that FedCCFA significantly outperforms existing methods under various concept drift settings. Code is available at https://github.com/Chen-Junbao/FedCCFA.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 34 of its 50 references that are in the map. First posted on arXiv 24 Oct 2024.

Builds on

34 of 50 references.

References · 34

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  3. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  4. 2020Adaptive Federated Optimizationcited by 1,046
  5. 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 906
  6. 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 851
  7. 2021Model-Contrastive Federated Learningcited by 766
  8. 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 672
  9. 2020Personalized Federated Learning with Moreau Envelopescited by 618
  10. 2018Federated Learning for Mobile Keyboard Predictioncited by 572
  11. 2020Federated Learning with Matched Averagingcited by 564
  12. 2021Federated Learning Based on Dynamic Regularizationcited by 562
22 more
  1. 2021Exploiting Shared Representations for Personalized Federated Learningcited by 541
  2. 2020An Efficient Framework for Clustered Federated Learningcited by 511
  3. 2019Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraintscited by 503
  4. 2020Learning under Concept Drift: A Reviewcited by 477
  5. 2019Bayesian Nonparametric Federated Learning of Neural Networkscited by 387
  6. 2020Three Approaches for Personalization with Applications to Federated Learningcited by 325
  7. 2020Personalized Federated Learning with First Order Model Optimizationcited by 201
  8. 2021FedBABU: Towards Enhanced Representation for Federated Image Classificationcited by 182
  9. 2019SlowMo: Improving Communication-Efficient Distributed SGD with Slow Momentumcited by 121
  10. 2021Local Learning Matters: Rethinking Data Heterogeneity in Federated Learningcited by 114
  11. 2023Personalized Federated Learning with Feature Alignment and Classifier Collaborationcited by 97
  12. 2023FedExP: Speeding Up Federated Averaging via Extrapolationcited by 69
  13. 2022FedFA: Federated Learning with Feature Anchors to Align Features and Classifiers for Heterogeneous Datacited by 50
  14. 2021Flexible Clustered Federated Learning for Client-Level Data Distribution Shiftcited by 47
  15. 2022DDG-DA: Data Distribution Generation for Predictable Concept Drift Adaptationcited by 36
  16. 2022Federated Learning under Distributed Concept Driftcited by 36
  17. 2021Concept drift detection and adaptation for federated and continual learningcited by 32
  18. 2022FedFM: Anchor-based Feature Matching for Data Heterogeneity in Federated Learningcited by 27
  19. 2021Towards Federated Learning on Time-Evolving Heterogeneous Datacited by 23
  20. 2023Online Boosting Adaptive Learning under Concept Drift for Multistream Classificationcited by 17
  21. 2021Asynchronous Federated Learning for Sensor Data with Concept Driftcited by 14
  22. 2016On perfect clustering of high dimension, low sample size datacited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 6; 2026: 2.

8 papers.

  1. 2025RCCDA: Adaptive Model Updates in the Presence of Concept Drift under a Constrained Resource Budgetcited by 2
  2. 2025An Information-Theoretic Analysis for Federated Learning under Concept Driftcited by 2
  3. 2025C^2Prompt: Class-aware Client Knowledge Interaction for Federated Continual Learningcited by 2
  4. 2026Fed-ADE: Adaptive Learning Rate for Federated Post-adaptation under Distribution Shiftcited by 2
  5. 2025FedDAA: Dynamic Client Clustering for Concept Drift Adaptation in Federated Learningcited by 1
  6. 2025FedLLM-Align: Feature Extraction From Heterogeneous Clientscited by 0
  7. 2025Computation-aware Energy-harvesting Federated Learning with Pipelined Cyclic Schedulingcited by 0
  8. 2026Hierarchical Federated Learning with Dynamic Clustering and Adaptive Regularization for Robust Infrastructure Inspectioncited by 0