# Flashback: Understanding and Mitigating Forgetting in Federated Learning

arXiv: https://arxiv.org/abs/2402.05558 · HTML: https://mlsanity.com/paper/2402.05558/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 41 references that are in the map.
- First posted on arXiv 8 Feb 2024.

## Builds on (most cited first, 26 of 26)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Federated Learning: Strategies for Improving Communication Efficiency](https://mlsanity.com/paper/1610.05492/) (2016)
- [Continual Lifelong Learning with Neural Networks: A Review](https://mlsanity.com/paper/1802.07569/) (2018)
- [Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization](https://mlsanity.com/paper/2007.07481/) (2020)
- [Towards Federated Learning at Scale: System Design](https://mlsanity.com/paper/1902.01046/) (2019)
- [LEAF: A Benchmark for Federated Settings](https://mlsanity.com/paper/1812.01097/) (2018)
- [Model-Contrastive Federated Learning](https://mlsanity.com/paper/2103.16257/) (2021)
- [Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence](https://mlsanity.com/paper/1801.10112/) (2018)
- [Ensemble Distillation for Robust Model Fusion in Federated Learning](https://mlsanity.com/paper/2006.07242/) (2020)
- [Federated Learning with Matched Averaging](https://mlsanity.com/paper/2002.06440/) (2020)
- [Communication-Efficient On-Device Machine Learning: Federated Distillation and Augmentation under Non-IID Private Data](https://mlsanity.com/paper/1811.11479/) (2018)
- [Applied Federated Learning: Improving Google Keyboard Query Suggestions](https://mlsanity.com/paper/1812.02903/) (2018)
- [Federated Optimization:Distributed Optimization Beyond the Datacenter](https://mlsanity.com/paper/1511.03575/) (2015)
- [Rethinking Architecture Design for Tackling Data Heterogeneity in Federated Learning](https://mlsanity.com/paper/2106.06047/) (2021)
- [Stochastic Controlled Averaging for Federated Learning with Communication Compression](https://mlsanity.com/paper/2308.08165/) (2023)
- [Preservation of the Global Knowledge by Not-True Distillation in Federated Learning](https://mlsanity.com/paper/2106.03097/) (2021)
- [Acceleration of Federated Learning with Alleviated Forgetting in Local Training](https://mlsanity.com/paper/2203.02645/) (2022)
- [GradMA: A Gradient-Memory-based Accelerated Federated Learning with Alleviated Catastrophic Forgetting](https://mlsanity.com/paper/2302.14307/) (2023)
- [Resource-Efficient Federated Learning](https://mlsanity.com/paper/2111.01108/) (2021)
- [FedSAE: A Novel Self-Adaptive Federated Learning Framework in Heterogeneous Systems](https://mlsanity.com/paper/2104.07515/) (2021)
- [FilFL: Client Filtering for Optimized Client Participation in Federated Learning](https://mlsanity.com/paper/2302.06599/) (2023)
- [Stochastic, Distributed and Federated Optimization for Machine Learning](https://mlsanity.com/paper/1707.01155/) (2017)

## Built on by (most cited first, 4 of 4)

- [Where is the Testbed for my Federated Learning Research?](https://mlsanity.com/paper/2407.14154/) (2024)
- [FlexFed: Mitigating Catastrophic Forgetting in Heterogeneous Federated Learning in Pervasive Computing Environments](https://mlsanity.com/paper/2505.13576/) (2025)
- [FlashbackCL: Mitigating Temporal Forgetting in Federated Learning](https://mlsanity.com/paper/2606.03939/) (2026)
- [FedADB: Class Anchor-Driven Dual-Branch Federated Learning for Mitigating Forgetting](https://mlsanity.com/paper/2608.15310/) (2026)

## Abstract (arXiv)

In Federated Learning (FL), forgetting, or the loss of knowledge across rounds, hampers algorithm convergence, particularly in the presence of severe data heterogeneity among clients. This study explores the nuances of this issue, emphasizing the critical role of forgetting in FL's inefficient learning within heterogeneous data contexts. Knowledge loss occurs in both client-local updates and server-side aggregation steps; addressing one without the other fails to mitigate forgetting. We introduce a metric to measure forgetting granularly, ensuring distinct recognition amid new knowledge acquisition. Leveraging these insights, we propose Flashback, an FL algorithm with a dynamic distillation approach that is used to regularize the local models, and effectively aggregate their knowledge. Across different benchmarks, Flashback outperforms other methods, mitigates forgetting, and achieves faster round-to-target-accuracy, by converging in 6 to 16 rounds.