mlsanityData to 14 Oct 2026

Joint Domain-Class Modeling for Federated Learning Under Feature Skew

arXiv 2609.22932 ↗First posted 19 Sep 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) enables collaborative model training without centralizing private data, but performance often degrades under feature skew: clients share labels while the conditional input distributions pi(x!mid!y) vary due to latent, client-specific appearance factors. We propose Joint Domain-Class Federated Learning (JDFL), a lightweight, optimizer-agnostic extension that makes this latent domain variation usable without sharing raw data. JDFL first infers domain clusters called pseudo-domains from brief local update signals. It then expands the classifier head to output M× C, joint (domain-class) logits. This allows the model to represent domain-conditioned appearance while keeping a shared backbone. To train the expanded head we introduce two complementary supervision strategies based on simple intuitions: a similarity-aware soft-labeling that transfers evidence between nearby inferred domains while allowing domain-specific specialization, and a per-sample randomized target assignment that perturbs supervision across the joint outputs and serves as a low-cost training-time regularizer. JDFL integrates with existing standard FL methods (e.g., FedAvg, SCAFFOLD) with minimal changes. Empirically, both supervision modes consistently improve global test accuracy on standard domain-shifted image benchmarks; ablations and sensitivity studies show the gains stem from the proposed supervision and parametrization rather than mere capacity increase.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 29 of its 39 references that are in the map. First posted on arXiv 19 Sep 2026.

Builds on

29 of 39 references.

References · 29

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  4. 2018Federated Learning with Non-IID Datacited by 1,108
  5. 2021Model-Contrastive Federated Learningcited by 766
  6. 2020Ensemble Distillation for Robust Model Fusion in Federated Learningcited by 682
  7. 2017Federated Multi-Task Learningcited by 672
  8. 2018Federated Learning for Mobile Keyboard Predictioncited by 572
  9. 2021Federated Learning Based on Dynamic Regularizationcited by 562
  10. 2019Federated Learning with Personalization Layerscited by 541
  11. 2021Exploiting Shared Representations for Personalized Federated Learningcited by 541
  12. 2020An Efficient Framework for Clustered Federated Learningcited by 511
17 more
  1. 2019FedMD: Heterogenous Federated Learning via Model Distillationcited by 459
  2. 2021Data-Free Knowledge Distillation for Heterogeneous Federated Learningcited by 383
  3. 2020Personalized Federated Learning: A Meta-Learning Approachcited by 312
  4. 2019Improving Federated Learning Personalization via Model Agnostic Meta Learningcited by 269
  5. 2013Maxout Networkscited by 187
  6. 2021FedBABU: Towards Enhanced Representation for Federated Image Classificationcited by 182
  7. 2022FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correctioncited by 181
  8. 2018Federated Meta-Learning with Fast Convergence and Efficient Communicationcited by 155
  9. 2021Multi-Center Federated Learning: Clients Clustering for Better Personalizationcited by 113
  10. 2019Robust Federated Learning in a Heterogeneous Environmentcited by 90
  11. 2021FedProc: Prototypical Contrastive Federated Learning on Non-IID datacited by 81
  12. 2021Towards Fair Federated Learning with Zero-Shot Data Augmentationcited by 64
  13. 2021Collaborative Federated Learning For Healthcare: Multi-Modal COVID-19 Diagnosis at the Edgecited by 56
  14. 2021Federated Learning for Malware Detection in IoT Devicescited by 36
  15. 2019Federated User Representation Learningcited by 32
  16. 2019Federated Learning for Ranking Browser History Suggestionscited by 24
  17. 2024From Challenges and Pitfalls to Recommendations and Opportunities: Implementing Federated Learning in Healthcarecited by 16

Built on by

Not cited yet.