mlsanityData to 7 Oct 2026

Global Layers: Non-IID Tabular Federated Learning

arXiv 2305.19290 ↗First posted 29 May 2023cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Data heterogeneity between clients remains a key challenge in Federated Learning (FL), particularly in the case of tabular data. This work presents Global Layers (GL), a novel partial model personalization method robust in the presence of joint distribution P(X,Y) shift and mixed input/output spaces X × Y across clients. To the best of our knowledge, GL is the first method capable of supporting both client-exclusive features and classes. We introduce two new benchmark experiments for tabular FL naturally partitioned from existing real world datasets: i) UCI Covertype split into 4 clients by "wilderness area" feature, and ii) UCI Heart Disease, SAHeart, UCI Heart Failure, each as clients. Empirical results in these experiments in the full-participant setting show that GL achieves better outcomes than Federated Averaging (FedAvg) and local-only training, with some clients even performing better than their centralized baseline.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 80 of its 103 references that are in the map. First posted on arXiv 29 May 2023.

Builds on

80 of 103 references.

References · 80

  1. 2017Attention Is All You Needcited by 59,932
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  4. 2019Advances and Open Problems in Federated Learningcited by 3,021
  5. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  6. 2014How transferable are features in deep neural networks?cited by 1,216
  7. 2018Federated Learning with Non-IID Datacited by 1,099
  8. 2020In Search of Lost Domain Generalizationcited by 1,042
  9. 2020Adaptive Federated Optimizationcited by 1,036
  10. 2020Out-of-Distribution Generalization via Risk Extrapolation (REx)cited by 737
  11. 2021Revisiting Deep Learning Models for Tabular Datacited by 725
  12. 2022Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distributioncited by 722
38 more
  1. 2017Federated Multi-Task Learningcited by 669
  2. 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 665
  3. 2013Domain Generalization via Invariant Feature Representationcited by 622
  4. 2020Personalized Federated Learning with Moreau Envelopescited by 612
  5. 2017Self-Normalizing Neural Networkscited by 591
  6. 2021Federated Learning Based on Dynamic Regularizationcited by 555
  7. 2021Exploiting Shared Representations for Personalized Federated Learningcited by 537
  8. 2019Federated Learning with Personalization Layerscited by 533
  9. 2021Deep Neural Networks and Tabular Data: A Surveycited by 489
  10. 2019Agnostic Federated Learningcited by 451
  11. 2020Adaptive Personalized Federated Learningcited by 353
  12. 2021FedProto: Federated Prototype Learning across Heterogeneous Clientscited by 349
  13. 2021Federated Learning on Non-IID Data: A Surveycited by 345
  14. 2020Think Locally, Act Globally: Federated Learning with Local and Global Representationscited by 322
  15. 2020Three Approaches for Personalization with Applications to Federated Learningcited by 321
  16. 2021SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Trainingcited by 310
  17. 2020Personalized Federated Learning: A Meta-Learning Approachcited by 309
  18. 2020Personalized Cross-Silo Federated Learning on Non-IID Datacited by 282
  19. 2019Improving Federated Learning Personalization via Model Agnostic Meta Learningcited by 264
  20. 2020Federated Learning of a Mixture of Global and Local Modelscited by 208
  21. 2020Personalized Federated Learning with First Order Model Optimizationcited by 201
  22. 2021Federated Multi-Task Learning under a Mixture of Distributionscited by 189
  23. 2022On Embeddings for Numerical Features in Tabular Deep Learningcited by 185
  24. 2019Adaptive Gradient-Based Meta-Learning Methodscited by 183
  25. 2019FedHealth: A Federated Transfer Learning Framework for Wearable Healthcarecited by 182
  26. 2022Handling Distribution Shifts on Graphs: An Invariance Perspectivecited by 163
  27. 2018Federated Meta-Learning with Fast Convergence and Efficient Communicationcited by 154
  28. 2020Mime: Mimicking Centralized Stochastic Algorithms in Federated Learningcited by 152
  29. 2019On the Convergence of Local Descent Methods in Federated Learningcited by 150
  30. 2019Federated Evaluation of On-device Personalizationcited by 147
  31. 2020FedPD: A Federated Learning Framework with Optimal Rates and Adaptivity to Non-IID Datacited by 143
  32. 2020Salvaging Federated Learning by Local Adaptationcited by 142
  33. 2020Lower Bounds and Optimal Algorithms for Personalized Federated Learningcited by 122
  34. 2021Linear Convergence in Federated Learning: Tackling Client Heterogeneity and Sparse Gradientscited by 122
  35. 2021Local Learning Matters: Rethinking Data Heterogeneity in Federated Learningcited by 114
  36. 2022Federated Learning with Partial Model Personalizationcited by 114
  37. 2021Parameterized Knowledge Transfer for Personalized Federated Learningcited by 108
  38. 2021Distributionally Robust Federated Averagingcited by 104

50 most cited of 80 All 80 (JSON)

Built on by

Not cited yet.