mlsanityData to 7 Oct 2026

MAP: Model Aggregation and Personalization in Federated Learning with Incomplete Classes

arXiv 2404.09232 ↗First posted 14 Apr 2024cs.LG cs.DCcited by 7

Not on the map. Why?

Abstract (arXiv)

In some real-world applications, data samples are usually distributed on local devices, where federated learning (FL) techniques are proposed to coordinate decentralized clients without directly sharing users' private data. FL commonly follows the parameter server architecture and contains multiple personalization and aggregation procedures. The natural data heterogeneity across clients, i.e., Non-I.I.D. data, challenges both the aggregation and personalization goals in FL. In this paper, we focus on a special kind of Non-I.I.D. scene where clients own incomplete classes, i.e., each client can only access a partial set of the whole class set. The server aims to aggregate a complete classification model that could generalize to all classes, while the clients are inclined to improve the performance of distinguishing their observed classes. For better model aggregation, we point out that the standard softmax will encounter several problems caused by missing classes and propose "restricted softmax" as an alternative. For better model personalization, we point out that the hard-won personalized models are not well exploited and propose "inherited private model" to store the personalization experience. Our proposed algorithm named MAP could simultaneously achieve the aggregation and personalization goals in FL. Abundant experimental studies verify the superiorities of our algorithm.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 53 of its 84 references that are in the map. First posted on arXiv 14 Apr 2024.

Builds on

53 of 84 references.

References · 53

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  4. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  5. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  6. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  7. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  8. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,323
  9. 2014How transferable are features in deep neural networks?cited by 1,216
  10. 2018Federated Learning with Non-IID Datacited by 1,099
  11. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,054
  12. 2020Adaptive Federated Optimizationcited by 1,036
38 more
  1. 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 897
  2. 2018LEAF: A Benchmark for Federated Settingscited by 780
  3. 2021Model-Contrastive Federated Learningcited by 762
  4. 2020Ensemble Distillation for Robust Model Fusion in Federated Learningcited by 678
  5. 2017Federated Multi-Task Learningcited by 669
  6. 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 665
  7. 2020Personalized Federated Learning with Moreau Envelopescited by 612
  8. 2020Federated Learning with Matched Averagingcited by 564
  9. 2021Federated Learning Based on Dynamic Regularizationcited by 555
  10. 2021Exploiting Shared Representations for Personalized Federated Learningcited by 537
  11. 2021Towards Personalized Federated Learningcited by 462
  12. 2019FedMD: Heterogenous Federated Learning via Model Distillationcited by 454
  13. 2019Bayesian Nonparametric Federated Learning of Neural Networkscited by 385
  14. 2021FedProto: Federated Prototype Learning across Heterogeneous Clientscited by 349
  15. 2020Three Approaches for Personalization with Applications to Federated Learningcited by 321
  16. 2018Communication-Efficient On-Device Machine Learning: Federated Distillation and Augmentation under Non-IID Private Datacited by 242
  17. 2020Federated Learning of a Mixture of Global and Local Modelscited by 208
  18. 2019Federated Evaluation of On-device Personalizationcited by 147
  19. 2020Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspectivecited by 143
  20. 2020Salvaging Federated Learning by Local Adaptationcited by 142
  21. 2020Federated Visual Classification with Real-World Data Distributioncited by 126
  22. 2022Federated Class-Incremental Learningcited by 126
  23. 2019Federated Learning for Emoji Prediction in a Mobile Keyboardcited by 115
  24. 2021FedNLP: Benchmarking Federated Learning Methods for Natural Language Processing Taskscited by 84
  25. 2020Practical One-Shot Federated Learning for Cross-Silo Settingcited by 76
  26. 2022Personalized Federated Learning via Variational Bayesian Inferencecited by 68
  27. 2020Federated Learning with Only Positive Labelscited by 55
  28. 2017Personalized and Private Peer-to-Peer Machine Learningcited by 54
  29. 2019Private Federated Learning with Domain Adaptationcited by 36
  30. 2021FedCV: A Federated Learning Framework for Diverse Computer Vision Taskscited by 32
  31. 2020Temperature check: theory and practice for training models with softmax-cross-entropy lossescited by 31
  32. 2019Rethinking Softmax with Cross-Entropy: Neural Network Classifier as Mutual Information Estimatorcited by 25
  33. 2022Federated Learning with Position-Aware Neuronscited by 24
  34. 2019Federated Learning with Unbiased Gradient Aggregation and Controllable Meta Updatingcited by 22
  35. 2020Learning Adaptive Embedding Considering Incremental Classcited by 21
  36. 2021Collaborative Semantic Aggregation and Calibration for Federated Domain Generalizationcited by 16
  37. 2021On Bridging Generic and Personalized Federated Learning for Image Classificationcited by 15
  38. 2019Max-margin Class Imbalanced Learning with Gaussian Affinitycited by 7

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year

Citing papers per year: 2024: 5; 2025: 2.

7 papers.

  1. 2025Federated Client-tailored Adapter for Medical Image Segmentationcited by 3
  2. 2024Proposal Report for the 2nd SciCAP Competition 2024cited by 2
  3. 2024Exploring and Exploiting the Asymmetric Valley of Deep Neural Networkscited by 1
  4. 2024First Place Solution of 2023 Global Artificial Intelligence Technology Innovation Competition Track 1cited by 0
  5. 2024Second Place Solution of WSDM2023 Toloka Visual Question Answering Challengecited by 0
  6. 2024The Solution for the AIGC Inference Performance Optimization Competitioncited by 0
  7. 2025FairGFL: Privacy-Preserving Fairness-Aware Federated Learning with Overlapping Subgraphscited by 0