mlsanityData to 7 Oct 2026

Personalised Federated Learning On Heterogeneous Feature Spaces

arXiv 2301.11447 ↗First posted 26 Jan 2023cs.LG cs.AI stat.MLcited by 5

Not on the map. Why?

Abstract (arXiv)

Most personalised federated learning (FL) approaches assume that raw data of all clients are defined in a common subspace i.e. all clients store their data according to the same schema. For real-world applications, this assumption is restrictive as clients, having their own systems to collect and then store data, may use heterogeneous data representations. We aim at filling this gap. To this end, we propose a general framework coined FLIC that maps client's data onto a common feature space via local embedding functions. The common feature space is learnt in a federated manner using Wasserstein barycenters while the local embedding functions are trained on each client via distribution alignment. We integrate this distribution alignement mechanism into a federated learning approach and provide the algorithmics of FLIC. We compare its performances against FL benchmarks involving heterogeneous input features spaces. In addition, we provide theoretical insights supporting the relevance of our methodology.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 50 of its 89 references that are in the map. First posted on arXiv 26 Jan 2023.

Builds on

50 of 89 references.

References · 50

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2019Advances and Open Problems in Federated Learningcited by 3,021
  4. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  5. 2018LEAF: A Benchmark for Federated Settingscited by 780
  6. 2018Computational Optimal Transportcited by 765
  7. 2022Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distributioncited by 722
  8. 2021Exploiting Shared Representations for Personalized Federated Learningcited by 537
  9. 2021Towards Personalized Federated Learningcited by 462
  10. 2020TextCaps: a Dataset for Image Captioning with Reading Comprehensioncited by 398
  11. 2020HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clientscited by 334
  12. 2019On Mutual Information Maximization for Representation Learningcited by 315
38 more
  1. 2019Improving Federated Learning Personalization via Model Agnostic Meta Learningcited by 264
  2. 2021No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Datacited by 241
  3. 2021Personalized Federated Learning using Hypernetworkscited by 210
  4. 2020Federated Learning of a Mixture of Global and Local Modelscited by 208
  5. 2017Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learningcited by 192
  6. 2019Adaptive Gradient-Based Meta-Learning Methodscited by 183
  7. 2021FedBABU: Towards Enhanced Representation for Federated Image Classificationcited by 180
  8. 2017Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryptioncited by 174
  9. 2021Distribution Matching for Heterogeneous Multi-Task Learning: a Large-scale Face Studycited by 168
  10. 2022Diverse Weight Averaging for Out-of-Distribution Generalizationcited by 148
  11. 2020Lower Bounds and Optimal Algorithms for Personalized Federated Learningcited by 122
  12. 2018Gromov-Wasserstein Alignment of Word Embedding Spacescited by 119
  13. 2021Parameterized Knowledge Transfer for Personalized Federated Learningcited by 108
  14. 2014Word Representations via Gaussian Embeddingcited by 96
  15. 2018Unsupervised Alignment of Embeddings with Wasserstein Procrustescited by 96
  16. 2021PPFL: Privacy-preserving Federated Learning with Trusted Execution Environmentscited by 93
  17. 2018MOABB: Trustworthy algorithm benchmarking for BCIscited by 80
  18. 2021Federated Reconstruction: Partially Local Federated Learningcited by 78
  19. 2022FedAvg with Fine Tuning: Local Updates Lead to Representation Learningcited by 55
  20. 2019Learning Generative Models across Incomparable Spacescited by 53
  21. 2022FedFA: Federated Learning with Feature Anchors to Align Features and Classifiers for Heterogeneous Datacited by 49
  22. 2017Optimal transport for Gaussian mixture modelscited by 45
  23. 2022The Fundamental Price of Secure Aggregation in Differentially Private Federated Learningcited by 39
  24. 2021PyVertical: A Vertical Federated Learning Framework for Multi-headed SplitNNcited by 35
  25. 2021Personalized Federated Learning: A Unified Framework and Universal Optimization Techniquescited by 34
  26. 2022Efficient Split-Mix Federated Learning for On-Demand and In-Situ Customizationcited by 34
  27. 2018Towards Optimal Transport with Global Invariancescited by 33
  28. 2021Averaging on the Bures-Wasserstein manifold: dimension-free convergence of gradient descentcited by 32
  29. 2022Architecture Agnostic Federated Learning for Neural Networkscited by 30
  30. 2022FedFM: Anchor-based Feature Matching for Data Heterogeneity in Federated Learningcited by 27
  31. 2018Generalizing Point Embeddings using the Wasserstein Space of Elliptical Distributionscited by 20
  32. 2019Secure and Efficient Federated Transfer Learningcited by 20
  33. 2020Learning Autoencoders with Relational Regularizationcited by 20
  34. 2021Differentially Private Sliced Wasserstein Distancecited by 19
  35. 2020Asymmetric Private Set Intersection with Applications to Contact Tracing and Private Vertical Federated Machine Learningcited by 12
  36. 2022Continual Horizontal Federated Learning for Heterogeneous Datacited by 8
  37. 2021Multi-task Learning by Leveraging the Semantic Informationcited by 5
  38. 2014Efficient Gaussian Sampling for Solving Large-Scale Inverse Problems using MCMC Methodscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 1; 2025: 0; 2026: 2.

5 papers.

  1. 2023Scalable Optimal Transport Methods in Machine Learning: A Contemporary Surveycited by 27
  2. 2026Federated Imputation under Heterogeneous Feature Spacescited by 1
  3. 2023Global Layers: Non-IID Tabular Federated Learningcited by 0
  4. 2024Survey of Privacy Threats and Countermeasures in Federated Learningcited by 0
  5. 2026Fed-ReMasker: Federated Tabular Imputation under Feature-Level Missingnesscited by 0