mlsanityData to 14 Oct 2026

Bold but Cautious: Unlocking the Potential of Personalized Federated Learning through Cautiously Aggressive Collaboration

arXiv 2309.11103 ↗First posted 20 Sep 2023cs.LGcited by 23

Not on the map. Why?

Abstract (arXiv)

Personalized federated learning (PFL) reduces the impact of non-independent and identically distributed (non-IID) data among clients by allowing each client to train a personalized model when collaborating with others. A key question in PFL is to decide which parameters of a client should be localized or shared with others. In current mainstream approaches, all layers that are sensitive to non-IID data (such as classifier layers) are generally personalized. The reasoning behind this approach is understandable, as localizing parameters that are easily influenced by non-IID data can prevent the potential negative effect of collaboration. However, we believe that this approach is too conservative for collaboration. For example, for a certain client, even if its parameters are easily influenced by non-IID data, it can still benefit by sharing these parameters with clients having similar data distribution. This observation emphasizes the importance of considering not only the sensitivity to non-IID data but also the similarity of data distribution when determining which parameters should be localized in PFL. This paper introduces a novel guideline for client collaboration in PFL. Unlike existing approaches that prohibit all collaboration of sensitive parameters, our guideline allows clients to share more parameters with others, leading to improved model performance. Additionally, we propose a new PFL method named FedCAC, which employs a quantitative metric to evaluate each parameter's sensitivity to non-IID data and carefully selects collaborators based on this evaluation. Experimental results demonstrate that FedCAC enables clients to share more parameters with others, resulting in superior performance compared to state-of-the-art methods, particularly in scenarios where clients have diverse distributions.

Key facts. Cited by 23 papers in the map (data through 14 Oct 2026). Builds on 26 of its 41 references that are in the map. First posted on arXiv 20 Sep 2023.

Builds on

26 of 41 references.

References · 26

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 851
  4. 2018SNIP: Single-shot Network Pruning based on Connection Sensitivitycited by 812
  5. 2021Model-Contrastive Federated Learningcited by 766
  6. 2020Ensemble Distillation for Robust Model Fusion in Federated Learningcited by 682
  7. 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 672
  8. 2020The Future of Digital Health with Federated Learningcited by 633
  9. 2020Personalized Federated Learning with Moreau Envelopescited by 618
  10. 2021FedBN: Federated Learning on Non-IID Features via Local Batch Normalizationcited by 571
  11. 2019Importance Estimation for Neural Network Pruningcited by 541
  12. 2019Federated Learning with Personalization Layerscited by 541
14 more
  1. 2021Exploiting Shared Representations for Personalized Federated Learningcited by 541
  2. 2021FedProto: Federated Prototype Learning across Heterogeneous Clientscited by 352
  3. 2020Personalized Cross-Silo Federated Learning on Non-IID Datacited by 283
  4. 2020Personalized Federated Learning with First Order Model Optimizationcited by 201
  5. 2021Federated Learning for Open Bankingcited by 141
  6. 2020FedVision: An Online Visual Object Detection Platform Powered by Federated Learningcited by 124
  7. 2022Federated Learning with Partial Model Personalizationcited by 114
  8. 2022Layer-wised Model Aggregation for Personalized Federated Learningcited by 96
  9. 2021Adapt to Adaptation: Learning Personalization for Cross-Silo Federated Learningcited by 53
  10. 2023Efficient Personalized Federated Learning via Sparse Model-Adaptationcited by 38
  11. 2022Multi-Level Branched Regularization for Federated Learningcited by 34
  12. 2022Personalized Federated Learning With Graphcited by 29
  13. 2021Personalized Federated Learning with Contextualized Generalizationcited by 23
  14. 2022PATS: Sensitivity-aware Noisy Learning for Pretrained Language Modelscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 8; 2025: 8; 2026: 6.

23 papers.

Sort:

By area:

  1. 2023PFLlib: A Beginner-Friendly and Comprehensive Personalized Federated Learning Library and Benchmarkcited by 17
  2. 2024Decoupling General and Personalized Knowledge in Federated Learning via Additive and Low-Rank Decompositioncited by 15
  3. 2025S2FGL: Spatial Spectral Federated Graph Learningcited by 7
  4. 2024Free Lunch for Federated Remote Sensing Target Fine-Grained Classification: A Parameter-Efficient Frameworkcited by 6
  5. 2024Federated Distillation for Medical Image Classification: Towards Trustworthy Computer-Aided Diagnosiscited by 4
  6. 2025Behavioral Anomaly Detection in Distributed Systems via Federated Contrastive Learningcited by 4
  7. 2024The Diversity Bonus: Learning from Dissimilar Distributed Clients in Personalized Federated Learningcited by 3
  8. 2024Towards Layer-Wise Personalized Federated Learning: Adaptive Layer Disentanglement via Conflicting Gradientscited by 3
  9. 2024Tackling Feature-Classifier Mismatch in Federated Learning via Prompt-Driven Feature Transformationcited by 2
  10. 2024DualFed: Enjoying both Generalization and Personalization in Federated Learning via Hierachical Representationscited by 2
  11. 2025Enhancing Visual Representation with Textual Semantics: Textual Semantics-Powered Prototypes for Heterogeneous Federated Learningcited by 2
  12. 2025Leave it to the Specialist: Repair Sparse LLMs with Sparse Fine-Tuning via Sparsity Evolutioncited by 2
11 more
  1. 2026Tackling Resource-Constrained and Data-Heterogeneity in Federated Learning with Double-Weight Sparse Packcited by 2
  2. 2025Choice Outweighs Effort: Facilitating Complementary Knowledge Fusion in Federated Learning via Re-calibration and Merit-discriminationcited by 1
  3. 2025FedBiF: Communication-Efficient Federated Learning via Bits Freezingcited by 1
  4. 2026Towards Robust Personalized Federated Learning: Vulnerability Assessment and Defense Co-Designcited by 1
  5. 2024Recovering Global Data Distribution Locally in Federated Learningcited by 0
  6. 2025Addressing the Collaboration Dilemma in Low-Data Federated Learning via Transient Sparsitycited by 0
  7. 2025Learning to Collaborate Over Graphs: A Selective Federated Multi-Task Learning Approachcited by 0
  8. 2026FedPSA: Modeling Behavioral Staleness in Asynchronous Federated Learningcited by 0
  9. 2026Fed-GAME: Personalized Federated Learning with Graph Attention Mixture-of-Experts For Time-Series Forecastingcited by 0
  10. 2026From Coordinate Matching to Structural Alignment: Rethinking Prototype Alignment in Heterogeneous Federated Learningcited by 0
  11. 2026FM2: Unified Federated Foundation Models for Heterogeneous Multimodal Medical Imagingcited by 0