mlsanityData to 14 Oct 2026

Federated Learning of Shareable Bases for Personalization-Friendly Image Classification

arXiv 2304.07882 ↗First posted 16 Apr 2023cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Personalized federated learning (PFL) aims to harness the collective wisdom of clients' data while building personalized models tailored to individual clients' data distributions. Existing works offer personalization primarily to clients who participate in the FL process, making it hard to encompass new clients who were absent or newly show up. In this paper, we propose FedBasis, a novel PFL framework to tackle such a deficiency. FedBasis learns a set of few shareable ``basis'' models, which can be linearly combined to form personalized models for clients. Specifically for a new client, only a small set of combination coefficients, not the model weights, needs to be learned. This notion makes FedBasis more parameter-efficient, robust, and accurate than competitive PFL baselines, especially in the low data regime, without increasing the inference cost. To demonstrate the effectiveness and applicability of FedBasis, we also present a more practical PFL testbed for image classification, featuring larger data discrepancies across clients in both the image and label spaces as well as more faithful training and test splits.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 59 of its 76 references that are in the map. First posted on arXiv 16 Apr 2023.

Builds on

59 of 76 references.

References · 59

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  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. 2019Advances and Open Problems in Federated Learningcited by 3,046
  5. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  6. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,188
  7. 2020Adaptive Federated Optimizationcited by 1,046
  8. 2016HyperNetworkscited by 1,027
  9. 2017Deeper, Broader and Artier Domain Generalizationcited by 986
  10. 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 851
  11. 2017A Survey on Multi-Task Learningcited by 840
  12. 2017An Overview of Multi-Task Learning in Deep Neural Networkscited by 803
38 more
  1. 2018LEAF: A Benchmark for Federated Settingscited by 792
  2. 2017Federated Multi-Task Learningcited by 672
  3. 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 672
  4. 2020Personalized Federated Learning with Moreau Envelopescited by 618
  5. 2021FedBN: Federated Learning on Non-IID Features via Local Batch Normalizationcited by 571
  6. 2019Federated Learning with Personalization Layerscited by 541
  7. 2021Exploiting Shared Representations for Personalized Federated Learningcited by 541
  8. 2020An Efficient Framework for Clustered Federated Learningcited by 511
  9. 2019FedMD: Heterogenous Federated Learning via Model Distillationcited by 459
  10. 2020Adaptive Personalized Federated Learningcited by 358
  11. 2019Dynamic Convolution: Attention over Convolution Kernelscited by 356
  12. 2020Think Locally, Act Globally: Federated Learning with Local and Global Representationscited by 325
  13. 2020Personalized Federated Learning: A Meta-Learning Approachcited by 312
  14. 2020Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrievalcited by 309
  15. 2020Personalized Cross-Silo Federated Learning on Non-IID Datacited by 283
  16. 2019CondConv: Conditionally Parameterized Convolutions for Efficient Inferencecited by 273
  17. 2019Improving Federated Learning Personalization via Model Agnostic Meta Learningcited by 269
  18. 2021Personalized Federated Learning using Hypernetworkscited by 212
  19. 2020Federated Learning of a Mixture of Global and Local Modelscited by 210
  20. 2020Personalized Federated Learning with First Order Model Optimizationcited by 201
  21. 2021Federated Multi-Task Learning under a Mixture of Distributionscited by 192
  22. 2019Adaptive Gradient-Based Meta-Learning Methodscited by 183
  23. 2018Federated Meta-Learning with Fast Convergence and Efficient Communicationcited by 155
  24. 2019Federated Evaluation of On-device Personalizationcited by 147
  25. 2020Survey of Personalization Techniques for Federated Learningcited by 145
  26. 2020Salvaging Federated Learning by Local Adaptationcited by 142
  27. 2020Federated Visual Classification with Real-World Data Distributioncited by 128
  28. 2020Lower Bounds and Optimal Algorithms for Personalized Federated Learningcited by 123
  29. 2022Federated Learning with Partial Model Personalizationcited by 114
  30. 2016Synthesized Classifiers for Zero-Shot Learningcited by 113
  31. 2021Parameterized Knowledge Transfer for Personalized Federated Learningcited by 109
  32. 2022Layer-wised Model Aggregation for Personalized Federated Learningcited by 96
  33. 2016Towards the Science of Security and Privacy in Machine Learningcited by 89
  34. 2021Personalized Federated Learning with Gaussian Processescited by 76
  35. 2019Variational Federated Multi-Task Learningcited by 69
  36. 2021Personalized Federated Learning through Local Memorizationcited by 57
  37. 2021Adapt to Adaptation: Learning Personalization for Cross-Silo Federated Learningcited by 53
  38. 2021FedSoft: Soft Clustered Federated Learning with Proximal Local Updatingcited by 46

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year

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

6 papers.

  1. 2023Parameter Efficient Multi-task Model Fusion with Partial Linearizationcited by 65
  2. 2023Holistic Transfer: Towards Non-Disruptive Fine-Tuning with Partial Target Datacited by 7
  3. 2024Backpropagation-Free Multi-modal On-Device Model Adaptation via Cloud-Device Collaborationcited by 5
  4. 2023PPFL: A Personalized Federated Learning Framework for Heterogeneous Populationcited by 1
  5. 2025Federated Inverse Probability Treatment Weighting for Individual Treatment Effect Estimationcited by 1
  6. 2025Patient-Specific Autoregressive Models for Organ Motion Prediction in Radiotherapycited by 1