mlsanityData to 14 Oct 2026

FlashbackCL: Mitigating Temporal Forgetting in Federated Learning

arXiv 2606.03939 ↗First posted 2 Jun 2026cs.LG cs.AI cs.PFcited by 0

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) of foundation and edge models increasingly targets deployments where client data distributions drift over time, yet existing forgetting-mitigation methods assume each client's distribution is stationary. Flashback, the strongest recent FL method against cross-client (spatial) forgetting, uses monotonically accumulating per-class label counts as a knowledge proxy; this proxy becomes miscalibrated under temporal distribution shift and anchors the global model to an outdated class balance. We formalise temporal forgetting in FL with a per-phase metric isolated from protocol-level fluctuations and propose Flashback Continual Learning (FlashbackCL), a drop-in extension of Flashback with (i) temporally-decayed label counts; (ii) a device-aware replay buffer with Class-Balanced Reservoir Sampling (CBRS); and (iii) server-side active coreset curation on the public distillation set. The results show that FlashbackCL achieves 6.9% to 10.0% relative improvement relative to Flashback, on CIFAR-10 with 50 clients and three controlled temporal shift modes, while simultaneously reducing temporal forgetting by up to 68%. A 5-variant ablation identifies CBRS replay as the critical component. FlashbackCL also improves Flashback by 3.5 points on stationary CIFAR-100, suggesting that class-balanced replay regularises spatial heterogeneity as well as temporal shift.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 30 references that are in the map. First posted on arXiv 2 Jun 2026.

Builds on

23 of 30 references.

References · 23

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  4. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  5. 2019Advances and Open Problems in Federated Learningcited by 3,046
  6. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  7. 2016Learning without Forgettingcited by 2,496
  8. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,330
  9. 2019Towards Federated Learning at Scale: System Designcited by 832
  10. 2021Model-Contrastive Federated Learningcited by 766
  11. 2018Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigencecited by 742
  12. 2020Ensemble Distillation for Robust Model Fusion in Federated Learningcited by 682
11 more
  1. 2020Federated Learning with Matched Averagingcited by 564
  2. 2020Federated Continual Learning with Weighted Inter-client Transfercited by 161
  3. 2022Federated Class-Incremental Learningcited by 127
  4. 2019Scalable and Order-robust Continual Learning with Additive Parameter Decompositioncited by 125
  5. 2021Preservation of the Global Knowledge by Not-True Distillation in Federated Learningcited by 87
  6. 2023Better Generative Replay for Continual Federated Learningcited by 55
  7. 2022Acceleration of Federated Learning with Alleviated Forgetting in Local Trainingcited by 29
  8. 2021Resource-Efficient Federated Learningcited by 26
  9. 2023Federated Orthogonal Training: Mitigating Global Catastrophic Forgetting in Continual Federated Learningcited by 21
  10. 2025Accurate Forgetting for Heterogeneous Federated Continual Learningcited by 11
  11. 2024Flashback: Understanding and Mitigating Forgetting in Federated Learningcited by 4

Built on by

Not cited yet.