mlsanityData to 14 Oct 2026

Robust Federated Learning Under Real-World Client Churn

arXiv 2607.06979 ↗First posted 8 Jul 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) enables training shared models on private, on-device data, but production deployments remain constrained to slow, multi-day refresh cycles due to the complexity of coordinating massive client populations. For applications such as feed ranking, ad targeting, and personalized recommendation, model freshness: the ability to rapidly adapt to new user-local data is critical for maximizing objectives like click-through rate. This lag leaves models stale and unresponsive to volatile data distributions driven by viral trends and shifting user intent. Bridging this gap requires addressing three challenges overlooked by existing FL systems: transient client availability, dynamic data heterogeneity, and delays between model predictions and observable outcomes. We present FeLiX, an FL orchestration framework that minimizes wall-clock time-to-target accuracy on live interaction streams. FeLiX introduces three primitives: (i) streaming-aware availability tiers that leverage lightweight telemetry to identify ready clients at scale; (ii) fresh-utility selection, a dual-tier mechanism that prioritizes statistically valuable updates from devices able to meet tight refresh deadlines; and (iii) informativeness-aware, delay-robust aggregation that incorporates late, high-value updates containing ground-truth outcomes without biasing the global model toward stale distributions. Unlike prior systems that rely on unrealistic oracular knowledge of client availability, FeLiX achieves near-oracular performance in real-world settings. Across CIFAR-10, Google Speech, and realistic low-availability traces, FeLiX reduces wall-clock time-to-target accuracy by up to 2.37X while reducing communication bandwidth by 1.30X compared to state-of-the-art synchronous and asynchronous FL baselines.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 34 of its 52 references that are in the map. First posted on arXiv 8 Jul 2026.

Builds on

34 of 52 references.

References · 34

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2019Advances and Open Problems in Federated Learningcited by 3,046
  3. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  4. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,229
  5. 2020Adaptive Federated Optimizationcited by 1,046
  6. 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 906
  7. 2019Towards Federated Learning at Scale: System Designcited by 832
  8. 2018Speech Commands: A Dataset for Limited-Vocabulary Speech Recognitioncited by 752
  9. 2020Ensemble Distillation for Robust Model Fusion in Federated Learningcited by 682
  10. 2018Federated Learning for Mobile Keyboard Predictioncited by 572
  11. 2016Federated Optimization: Distributed Machine Learning for On-Device Intelligencecited by 564
  12. 2020Federated Learning with Matched Averagingcited by 564
22 more
  1. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 459
  2. 2020Flower: A Friendly Federated Learning Research Frameworkcited by 455
  3. 2019Bayesian Nonparametric Federated Learning of Neural Networkscited by 387
  4. 2018Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edgecited by 352
  5. 2019Asynchronous Federated Optimizationcited by 267
  6. 2021Federated Learning with Buffered Asynchronous Aggregationcited by 190
  7. 2021Federated Learning for Smart Healthcare: A Surveycited by 184
  8. 2019Federated Adversarial Domain Adaptationcited by 140
  9. 2016Distributed Mean Estimation with Limited Communicationcited by 136
  10. 2021FedScale: Benchmarking Model and System Performance of Federated Learning at Scalecited by 136
  11. 2021Papaya: Practical, Private, and Scalable Federated Learningcited by 90
  12. 2018Adaptive Communication Strategies to Achieve the Best Error-Runtime Trade-off in Local-Update SGDcited by 77
  13. 2020Practical One-Shot Federated Learning for Cross-Silo Settingcited by 77
  14. 2021On Large-Cohort Training for Federated Learningcited by 74
  15. 2019Federated Learning of N-gram Language Modelscited by 33
  16. 2016Asynchrony begets Momentum, with an Application to Deep Learningcited by 30
  17. 2023Asynchronous Federated Continual Learningcited by 29
  18. 2023TimelyFL: Heterogeneity-aware Asynchronous Federated Learning with Adaptive Partial Trainingcited by 27
  19. 2023FLINT: A Platform for Federated Learning Integrationcited by 17
  20. 2023Flame: Simplifying Topology Extension in Federated Learningcited by 7
  21. 2024FedStale: leveraging stale client updates in federated learningcited by 5
  22. 2024PAPAYA Federated Analytics Stack: Engineering Privacy, Scalability and Practicalitycited by 1

Built on by

Not cited yet.