mlsanityData to 7 Oct 2026

Communication-Efficient Federated AUC Maximization with Cyclic Client Participation

arXiv 2601.01649 ↗First posted 4 Jan 2026cs.LG cs.DCcited by 0

Not on the map. Why?

Abstract (arXiv)

Federated AUC maximization is a powerful approach for learning from imbalanced data in federated learning (FL). However, existing methods typically assume full client availability, which is rarely practical. In real-world FL systems, clients often participate in a cyclic manner: joining training according to a fixed, repeating schedule. This setting poses unique optimization challenges for the non-decomposable AUC objective. This paper addresses these challenges by developing and analyzing communication-efficient algorithms for federated AUC maximization under cyclic client participation. We investigate two key settings: First, we study AUC maximization with a squared surrogate loss, which reformulates the problem as a nonconvex-strongly-concave minimax optimization. By leveraging the Polyak-Lojasiewicz (PL) condition, we establish a state-of-the-art communication complexity of widetildeO(1/ε1/2) and iteration complexity of widetildeO(1/ε). Second, we consider general pairwise AUC losses. We establish a communication complexity of O(1/ε3) and an iteration complexity of O(1/ε4). Further, under the PL condition, these bounds improve to communication complexity of widetildeO(1/ε1/2) and iteration complexity of widetildeO(1/ε). Extensive experiments on benchmark tasks in image classification, medical imaging, and fraud detection demonstrate the superior efficiency and effectiveness of our proposed methods.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 48 of its 71 references that are in the map. First posted on arXiv 4 Jan 2026.

Builds on

48 of 71 references.

References · 48

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2016Densely Connected Convolutional Networkscited by 6,691
  4. 2019Advances and Open Problems in Federated Learningcited by 3,021
  5. 2016Deep Learning with Differential Privacycited by 2,682
  6. 2019Deep Leakage from Gradientscited by 1,004
  7. 2021MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classificationcited by 682
  8. 2018Local SGD Converges Fast and Communicates Littlecited by 595
  9. 2018Federated Learning for Mobile Keyboard Predictioncited by 565
  10. 2016Federated Optimization: Distributed Machine Learning for On-Device Intelligencecited by 558
  11. 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 528
  12. 2019Agnostic Federated Learningcited by 451
36 more
  1. 2017Sampling Matters in Deep Embedding Learningcited by 285
  2. 2018Parallel Restarted SGD with Faster Convergence and Less Communication: Demystifying Why Model Averaging Works for Deep Learningcited by 277
  3. 2018Applied Federated Learning: Improving Google Keyboard Query Suggestionscited by 202
  4. 2020Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategiescited by 196
  5. 2021Achieving Linear Speedup with Partial Worker Participation in Non-IID Federated Learningcited by 192
  6. 2019On the Linear Speedup Analysis of Communication Efficient Momentum SGD for Distributed Non-Convex Optimizationcited by 178
  7. 2021Practical and Private (Deep) Learning without Sampling or Shufflingcited by 169
  8. 2020LDP-Fed: Federated Learning with Local Differential Privacycited by 129
  9. 2021Papaya: Practical, Private, and Scalable Federated Learningcited by 89
  10. 2020Large-scale Robust Deep AUC Maximization: A New Surrogate Loss and Empirical Studies on Medical Image Classificationcited by 84
  11. 2021Federated Evaluation and Tuning for On-Device Personalization: System Design & Applicationscited by 84
  12. 2022Federated Learning Enables Big Data for Rare Cancer Boundary Detectioncited by 83
  13. 2020Towards Flexible Device Participation in Federated Learningcited by 64
  14. 2019Active Federated Learningcited by 63
  15. 2022FedVARP: Tackling the Variance Due to Partial Client Participation in Federated Learningcited by 62
  16. 2016CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examplescited by 58
  17. 2019On Symmetric Losses for Learning from Corrupted Labelscited by 53
  18. 2022A Unified Analysis of Federated Learning with Arbitrary Client Participationcited by 45
  19. 2013One-Pass AUC Optimizationcited by 42
  20. 2021Local Stochastic Gradient Descent Ascent: Convergence Analysis and Communication Efficiencycited by 40
  21. 2023FedML-HE: An Efficient Homomorphic-Encryption-Based Privacy-Preserving Federated Learning Systemcited by 38
  22. 2022Federated Minimax Optimization: Improved Convergence Analyses and Algorithmscited by 37
  23. 2023On the Convergence of Federated Averaging with Cyclic Client Participationcited by 31
  24. 2020Communication-Efficient Distributed Stochastic AUC Maximization with Deep Neural Networkscited by 27
  25. 2021Federated Deep AUC Maximization for Heterogeneous Data with a Constant Communication Complexitycited by 21
  26. 2021Simple Stochastic and Online Gradient Descent Algorithms for Pairwise Learningcited by 20
  27. 2020Fast Objective & Duality Gap Convergence for Non-Convex Strongly-Concave Min-Max Problems with PL Conditioncited by 19
  28. 2023Randomized Quantization is All You Need for Differential Privacy in Federated Learningcited by 16
  29. 2022Benchmarking Deep AUROC Optimization: Loss Functions and Algorithmic Choicescited by 10
  30. 2022FeDXL: Provable Federated Learning for Deep X-Risk Optimizationcited by 10
  31. 2024Federated Learning under Periodic Client Participation and Heterogeneous Data: A New Communication-Efficient Algorithm and Analysiscited by 8
  32. 2024The Effect of Quantization in Federated Learning: A R'enyi Differential Privacy Perspectivecited by 6
  33. 2015To Drop or Not to Drop: Robustness, Consistency and Differential Privacy Properties of Dropoutcited by 4
  34. 2022FedGRec: Federated Graph Recommender System with Lazy Update of Latent Embeddingscited by 4
  35. 2022Communication-Efficient Local SGD with Age-Based Worker Selectioncited by 3
  36. 2025Enhancing Model Privacy in Federated Learning with Random Masking and Quantizationcited by 1

Built on by

Not cited yet.