mlsanityData to 7 Oct 2026

Client-Conditional Federated Learning via Local Training Data Statistics

arXiv 2603.11307 ↗First posted 11 Mar 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) under data heterogeneity remains challenging: existing methods either ignore client differences (FedAvg), require costly cluster discovery (IFCA), or maintain per-client models (Ditto). All degrade when data is sparse or heterogeneity is multi-dimensional. We propose conditioning a single global model on locally-computed PCA statistics of each client's training data, requiring zero additional communication. Evaluating across 97~configurations spanning four heterogeneity types (label shift, covariate shift, concept shift, and combined heterogeneity), four datasets (MNIST, Fashion-MNIST, CIFAR-10, CIFAR-100), and seven FL baseline methods, we find that our method matches the Oracle baseline -- which knows true cluster assignments -- across all settings, surpasses it by 1--6% on combined heterogeneity where continuous statistics are richer than discrete cluster identifiers, and is uniquely sparsity-robust among all tested methods.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 22 of its 30 references that are in the map. First posted on arXiv 11 Mar 2026.

Builds on

22 of 30 references.

References · 22

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  4. 2019Advances and Open Problems in Federated Learningcited by 3,021
  5. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,286
  6. 2018Federated Learning with Non-IID Datacited by 1,099
  7. 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 836
  8. 2017Federated Multi-Task Learningcited by 669
  9. 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 665
  10. 2020Personalized Federated Learning with Moreau Envelopescited by 612
  11. 2020An Efficient Framework for Clustered Federated Learningcited by 505
  12. 2019Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraintscited by 499
10 more
  1. 2017Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descentcited by 496
  2. 2021Towards Personalized Federated Learningcited by 462
  3. 2021Federated Multi-Task Learning under a Mixture of Distributionscited by 189
  4. 2022Personalized PCA: Decoupling Shared and Unique Featurescited by 17
  5. 2024Personalized Federated Learning via Feature Distribution Adaptationcited by 13
  6. 2022Decentralized adaptive clustering of deep nets is beneficial for client collaborationcited by 7
  7. 2023Efficient Node Selection in Private Personalized Decentralized Learningcited by 4
  8. 2025Federated Learning Survey: A Multi-Level Taxonomy of Aggregation Techniques, Experimental Insights, and Future Frontierscited by 3
  9. 2019Communication-Efficient Distributed Optimization in Networks with Gradient Tracking and Variance Reductioncited by 1
  10. 2025Conditioning on Local Statistics for Scalable Heterogeneous Federated Learningcited by 1

Built on by

Not cited yet.