mlsanityData to 14 Oct 2026

A Taxonomy and Resolution Strategy for Client-Level Disagreements in Federated Learning

arXiv 2604.23386 ↗First posted 25 Apr 2026cs.DC cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) typically assumes unconditional collaboration, a premise that overlooks the complexities of real-world, multi-stakeholder environments in which clients may need to exclude one another for strategic, regulatory, or competitive reasons. This paper addresses this gap, which we term 'client-level disagreements,' by first introducing a taxonomy of such scenarios. We then propose a robust, multi-track resolution strategy that guarantees strict client exclusion by creating and managing isolated model update paths ('tracks'), thereby preventing the cross-contamination and unfairness issues present in naive strategies. Through an empirical evaluation of our custom simulation system across 34 scenarios using the MNIST and N-CMAPSS datasets, we validate that our approach correctly handles permanent, temporal, and overlapping disagreement patterns. Our scalability analysis reveals the server-side resolution algorithm's overhead is negligible (<1 ms per round) even under heavy load. The primary scalability constraint is the client-side training load from participating in multiple tracks, a cost that we show can be effectively mitigated by a submodel reuse strategy. This work presents a scalable and architecturally sound method for managing client-level disagreements, and enhances the practical applicability of FL in settings where policy compliance and strategic control are non-negotiable.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 17 of its 29 references that are in the map. First posted on arXiv 25 Apr 2026.

Builds on

17 of 29 references.

References · 17

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2020Personalized Federated Learning with Moreau Envelopescited by 618
  3. 2020An Efficient Framework for Clustered Federated Learningcited by 511
  4. 2019Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraintscited by 503
  5. 2020Adaptive Personalized Federated Learningcited by 358
  6. 2020Personalized Federated Learning: A Meta-Learning Approachcited by 312
  7. 2022Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learningcited by 172
  8. 2022FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extractioncited by 102
  9. 2023A Survey on Federated Unlearning: Challenges, Methods, and Future Directionscited by 63
  10. 2022VeriFi: Towards Verifiable Federated Unlearningcited by 46
  11. 2020Dynamic Clustering in Federated Learningcited by 27
  12. 2024FIARSE: Model-Heterogeneous Federated Learning via Importance-Aware Submodel Extractioncited by 21
5 more
  1. 2023Share Your Representation Only: Guaranteed Improvement of the Privacy-Utility Tradeoff in Federated Learningcited by 13
  2. 2022Energy-Aware Edge Association for Cluster-based Personalized Federated Learningcited by 6
  3. 2022HetVis: A Visual Analysis Approach for Identifying Data Heterogeneity in Horizontal Federated Learningcited by 6
  4. 2022Hierarchical Federated Learning with Momentum Acceleration in Multi-Tier Networkscited by 6
  5. 2021Federated Submodel Optimization for Hot and Cold Data Featurescited by 4

Built on by

Not cited yet.