mlsanityData to 14 Oct 2026

pFedSim: Similarity-Aware Model Aggregation Towards Personalized Federated Learning

arXiv 2305.15706 ↗First posted 25 May 2023cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

The federated learning (FL) paradigm emerges to preserve data privacy during model training by only exposing clients' model parameters rather than original data. One of the biggest challenges in FL lies in the non-IID (not identical and independently distributed) data (a.k.a., data heterogeneity) distributed on clients. To address this challenge, various personalized FL (pFL) methods are proposed such as similarity-based aggregation and model decoupling. The former one aggregates models from clients of a similar data distribution. The later one decouples a neural network (NN) model into a feature extractor and a classifier. Personalization is captured by classifiers which are obtained by local training. To advance pFL, we propose a novel pFedSim (pFL based on model similarity) algorithm in this work by combining these two kinds of methods. More specifically, we decouple a NN model into a personalized feature extractor, obtained by aggregating models from similar clients, and a classifier, which is obtained by local training and used to estimate client similarity. Compared with the state-of-the-art baselines, the advantages of pFedSim include: 1) significantly improved model accuracy; 2) low communication and computation overhead; 3) a low risk of privacy leakage; 4) no requirement for any external public information. To demonstrate the superiority of pFedSim, extensive experiments are conducted on real datasets. The results validate the superb performance of our algorithm which can significantly outperform baselines under various heterogeneous data settings.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 37 of its 47 references that are in the map. First posted on arXiv 25 May 2023.

Builds on

37 of 47 references.

References · 37

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  4. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  5. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  6. 2019Similarity of Neural Network Representations Revisitedcited by 1,755
  7. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,331
  8. 2018Federated Learning with Non-IID Datacited by 1,108
  9. 2019Deep Leakage from Gradientscited by 1,021
  10. 2018On First-Order Meta-Learning Algorithmscited by 1,018
  11. 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 851
  12. 2021Model-Contrastive Federated Learningcited by 766
25 more
  1. 2017Federated Multi-Task Learningcited by 672
  2. 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 672
  3. 2021FedBN: Federated Learning on Non-IID Features via Local Batch Normalizationcited by 571
  4. 2021Federated Learning Based on Dynamic Regularizationcited by 562
  5. 2019Federated Learning with Personalization Layerscited by 541
  6. 2021Exploiting Shared Representations for Personalized Federated Learningcited by 541
  7. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 520
  8. 2019Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraintscited by 503
  9. 2019FedMD: Heterogenous Federated Learning via Model Distillationcited by 459
  10. 2021Data-Free Knowledge Distillation for Heterogeneous Federated Learningcited by 383
  11. 2020Adaptive Personalized Federated Learningcited by 358
  12. 2021FedProto: Federated Prototype Learning across Heterogeneous Clientscited by 352
  13. 2019Improving Federated Learning Personalization via Model Agnostic Meta Learningcited by 269
  14. 2021No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Datacited by 241
  15. 2021Personalized Federated Learning using Hypernetworkscited by 212
  16. 2020Federated Learning of a Mixture of Global and Local Modelscited by 210
  17. 2020Personalized Federated Learning with First Order Model Optimizationcited by 201
  18. 2021FedBABU: Towards Enhanced Representation for Federated Image Classificationcited by 182
  19. 2021Local Learning Matters: Rethinking Data Heterogeneity in Federated Learningcited by 114
  20. 2021Parameterized Knowledge Transfer for Personalized Federated Learningcited by 109
  21. 2022Federated Learning with Label Distribution Skew via Logits Calibrationcited by 109
  22. 2022Layer-wised Model Aggregation for Personalized Federated Learningcited by 96
  23. 2021Federated Reconstruction: Partially Local Federated Learningcited by 79
  24. 2021Personalized Federated Learning with Adaptive Batchnorm for Healthcarecited by 26
  25. 2021On Bridging Generic and Personalized Federated Learning for Image Classificationcited by 15

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 3; 2025: 3; 2026: 2.

9 papers.

  1. 2024Unlocking the Potential of Model Calibration in Federated Learningcited by 3
  2. 2025Quantifying Data Similarity Using Cross Learningcited by 3
  3. 2023Adaptive Model Pruning and Personalization for Federated Learning over Wireless Networkscited by 2
  4. 2024Towards Optimal Customized Architecture for Heterogeneous Federated Learning with Contrastive Cloud-Edge Model Decouplingcited by 2
  5. 2025FL-PLAS: Federated Learning with Partial Layer Aggregation for Backdoor Defense Against High-Ratio Malicious Clientscited by 1
  6. 2024MAPL: Model Agnostic Peer-to-peer Learningcited by 0
  7. 2025Lazy But Effective: Collaborative Personalized Federated Learning with Heterogeneous Datacited by 0
  8. 2026FedOBP: Federated Optimal Brain Personalization through Cloud-Edge Element-wise Decouplingcited by 0
  9. 2026Personalized Federated Learning through Global Knowledge Distillation and Local Head Adaptationcited by 0