mlsanityData to 7 Oct 2026

PFSL: Personalized & Fair Split Learning with Data & Label Privacy for thin clients

arXiv 2303.10624 ↗First posted 19 Mar 2023cs.LG cs.DCcited by 3

Not on the map. Why?

Abstract (arXiv)

The traditional framework of federated learning (FL) requires each client to re-train their models in every iteration, making it infeasible for resource-constrained mobile devices to train deep-learning (DL) models. Split learning (SL) provides an alternative by using a centralized server to offload the computation of activations and gradients for a subset of the model but suffers from problems of slow convergence and lower accuracy. In this paper, we implement PFSL, a new framework of distributed split learning where a large number of thin clients perform transfer learning in parallel, starting with a pre-trained DL model without sharing their data or labels with a central server. We implement a lightweight step of personalization of client models to provide high performance for their respective data distributions. Furthermore, we evaluate performance fairness amongst clients under a work fairness constraint for various scenarios of non-i.i.d. data distributions and unequal sample sizes. Our accuracy far exceeds that of current SL algorithms and is very close to that of centralized learning on several real-life benchmarks. It has a very low computation cost compared to FL variants and promises to deliver the full benefits of DL to extremely thin, resource-constrained clients.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 34 of its 53 references that are in the map. First posted on arXiv 19 Mar 2023.

Builds on

34 of 53 references.

References · 34

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  4. 2018Federated Learning with Non-IID Datacited by 1,099
  5. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 707
  6. 2017Federated Multi-Task Learningcited by 669
  7. 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 665
  8. 2021Federated Learning on Non-IID Data Silos: An Experimental Studycited by 566
  9. 2020An Efficient Framework for Clustered Federated Learningcited by 505
  10. 2019Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraintscited by 499
  11. 2021Towards Personalized Federated Learningcited by 462
  12. 2019Agnostic Federated Learningcited by 451
22 more
  1. 2018Split learning for health: Distributed deep learning without sharing raw patient datacited by 391
  2. 2019Fair Resource Allocation in Federated Learningcited by 389
  3. 2018Fairness Without Demographics in Repeated Loss Minimizationcited by 363
  4. 2020Personalized Federated Learning: A Meta-Learning Approachcited by 309
  5. 2020SplitFed: When Federated Learning Meets Split Learningcited by 308
  6. 2019Improving Federated Learning Personalization via Model Agnostic Meta Learningcited by 264
  7. 2021Federated Learning for Smart Healthcare: A Surveycited by 182
  8. 2019Federated Evaluation of On-device Personalizationcited by 147
  9. 2020Salvaging Federated Learning by Local Adaptationcited by 142
  10. 2021Label Leakage and Protection in Two-party Split Learningcited by 87
  11. 2019Detailed comparison of communication efficiency of split learning and federated learningcited by 76
  12. 2019Split Learning for collaborative deep learning in healthcarecited by 72
  13. 2020End-to-End Evaluation of Federated Learning and Split Learning for Internet of Thingscited by 64
  14. 2021Collaborative Federated Learning For Healthcare: Multi-Modal COVID-19 Diagnosis at the Edgecited by 56
  15. 2018Algorithms that Remember: Model Inversion Attacks and Data Protection Lawcited by 52
  16. 2020Federated Transfer Learning: concept and applicationscited by 32
  17. 2018No Peek: A Survey of private distributed deep learningcited by 30
  18. 2022Differentially Private Label Protection in Split Learningcited by 25
  19. 2021Server-Side Local Gradient Averaging and Learning Rate Acceleration for Scalable Split Learningcited by 22
  20. 2021SplitGuard: Detecting and Mitigating Training-Hijacking Attacks in Split Learningcited by 20
  21. 2022Combined Federated and Split Learning in Edge Computing for Ubiquitous Intelligence in Internet of Things: State of the Art and Future Directionscited by 14
  22. 2022Straggler-Resilient Personalized Federated Learningcited by 9

Built on by

Cited by year

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

3 papers.

  1. 2023Optimal Resource Allocation for U-Shaped Parallel Split Learningcited by 33
  2. 2024SplitLLM: Collaborative Inference of LLMs for Model Placement and Throughput Optimizationcited by 10
  3. 2023Adaptive Compression-Aware Split Learning and Inference for Enhanced Network Efficiencycited by 8