# FlexFed: Mitigating Catastrophic Forgetting in Heterogeneous Federated Learning in Pervasive Computing Environments

arXiv: https://arxiv.org/abs/2505.13576 · HTML: https://mlsanity.com/paper/2505.13576/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 43 references that are in the map.
- First posted on arXiv 19 May 2025.

## Builds on (most cited first, 28 of 28)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [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)
- [Federated Learning with Non-IID Data](https://mlsanity.com/paper/1806.00582/) (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)
- [Local SGD Converges Fast and Communicates Little](https://mlsanity.com/paper/1805.09767/) (2018)
- [Federated Learning with Matched Averaging](https://mlsanity.com/paper/2002.06440/) (2020)
- [Federated Learning Based on Dynamic Regularization](https://mlsanity.com/paper/2111.04263/) (2021)
- [FedMD: Heterogenous Federated Learning via Model Distillation](https://mlsanity.com/paper/1910.03581/) (2019)
- [Achieving Linear Speedup with Partial Worker Participation in Non-IID Federated Learning](https://mlsanity.com/paper/2101.11203/) (2021)
- [FedBE: Making Bayesian Model Ensemble Applicable to Federated Learning](https://mlsanity.com/paper/2009.01974/) (2020)
- [FedScale: Benchmarking Model and System Performance of Federated Learning at Scale](https://mlsanity.com/paper/2105.11367/) (2021)
- [Overcoming Forgetting in Federated Learning on Non-IID Data](https://mlsanity.com/paper/1910.07796/) (2019)
- [Preservation of the Global Knowledge by Not-True Distillation in Federated Learning](https://mlsanity.com/paper/2106.03097/) (2021)
- [Fast Federated Learning in the Presence of Arbitrary Device Unavailability](https://mlsanity.com/paper/2106.04159/) (2021)
- [Better Generative Replay for Continual Federated Learning](https://mlsanity.com/paper/2302.13001/) (2023)
- [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)
- [Federated Learning for Data Streams](https://mlsanity.com/paper/2301.01542/) (2023)
- [DYNAMITE: Dynamic Interplay of Mini-Batch Size and Aggregation Frequency for Federated Learning with Static and Streaming Dataset](https://mlsanity.com/paper/2310.14906/) (2023)
- [On the Local Cache Update Rules in Streaming Federated Learning](https://mlsanity.com/paper/2303.16340/) (2023)
- [To Store or Not? Online Data Selection for Federated Learning with Limited Storage](https://mlsanity.com/paper/2209.00195/) (2022)
- [Addressing Client Drift in Federated Continual Learning with Adaptive Optimization](https://mlsanity.com/paper/2203.13321/) (2022)
- [Flashback: Understanding and Mitigating Forgetting in Federated Learning](https://mlsanity.com/paper/2402.05558/) (2024)
- [A Framework for Realistic Simulation of Daily Human Activity](https://mlsanity.com/paper/2311.15400/) (2023)

## Abstract (arXiv)

Federated Learning (FL) enables collaborative model training while preserving privacy by allowing clients to share model updates instead of raw data. Pervasive computing environments (e.g., for Human Activity Recognition, HAR), which we focus on in this paper, are characterized by resource-constrained end devices, streaming sensor data and intermittent client participation. Variations in user behavior, common in HAR environments, often result in non-stationary data distributions. As such, existing FL approaches face challenges in HAR settings due to differing assumptions. The combined effects of HAR characteristics, namely heterogeneous data and intermittent participation, can lead to a severe issue called catastrophic forgetting (CF). Unlike Continuous Learning (CL), which addresses CF using memory and replay mechanisms, FL's privacy constraints prohibit such strategies. To tackle CF in HAR environments, we propose FlexFed, a novel FL approach that prioritizes data retention for efficient memory use and dynamically adjusts offline training frequency based on distribution shifts, client capability and offline duration. To better quantify CF in FL, we introduce a new metric that accounts for under-represented data, enabling more accurate evaluations. We also develop a realistic HAR-based evaluation framework that simulates streaming data, dynamic distributions, imbalances and varying availability. Experiments show that FlexFed mitigates CF more effectively, improves FL efficiency by 10 to 15 % and achieves faster, more stable convergence, especially for infrequent or under-represented data.