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

• URL: http://arxiv.org/abs/2505.13576v1
• Date: Mon, 19 May 2025 14:23:37 GMT
• Title: FlexFed: Mitigating Catastrophic Forgetting in Heterogeneous Federated Learning in Pervasive Computing Environments
• Authors: Sara Alosaime, Arshad Jhumka,
• Abstract summary: Pervasive computing environments (e.g., for Human Activity Recognition, HAR) are characterized by resource-constrained end devices, streaming sensor data and intermittent client participation.<n>We propose FlexFed, a novel FL approach that prioritizes data retention for efficient memory use and dynamically adjusts offline training frequency.<n>We also develop a realistic HAR-based evaluation framework that simulates streaming data, dynamic distributions, imbalances and varying availability.
• Score: 4.358456799125694
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• FedWCM: Unleashing the Potential of Momentum-based Federated Learning in Long-Tailed Scenarios [14.18492489954482]
  Federated Learning (FL) enables decentralized model training while preserving data privacy.<n>Despite its benefits, FL faces challenges with non-identically distributed (non-IID) data.<n>We propose FedWCM, a method that dynamically adjusts momentum using global and per-round data.
  arXiv  Detail & Related papers  (2025-07-20T14:24:57Z)
• Shift Happens: Mixture of Experts based Continual Adaptation in Federated Learning [3.120955853908236]
  Federated Learning (FL) enables collaborative model training across decentralized clients without sharing raw data.<n>We introduce ShiftEx, a shift-aware mixture of experts framework that creates and trains specialized global models in response to detected distribution shifts.<n>We demonstrate 5.5-12.9 percentage point accuracy improvements and 22-95 % faster adaptation compared to state-of-the-art FL baselines across diverse shift scenarios.
  arXiv  Detail & Related papers  (2025-06-23T15:59:21Z)
• Federated Loss Exploration for Improved Convergence on Non-IID Data [20.979550470097823]
  Federated Loss Exploration (FedLEx) is an innovative approach specifically designed to tackle these challenges.<n>FedLEx distinctively addresses the shortcomings of existing FL methods in non-IID settings.<n>Our experiments with state-of-the art FL algorithms demonstrate significant improvements in performance.
  arXiv  Detail & Related papers  (2025-06-23T13:42:07Z)
• FLea: Addressing Data Scarcity and Label Skew in Federated Learning via Privacy-preserving Feature Augmentation [15.298650496155508]
  Federated Learning (FL) enables model development by leveraging data distributed across numerous edge devices without transferring local data to a central server. Existing FL methods face challenges when dealing with scarce and label-skewed data across devices, resulting in local model overfitting and drift. We propose a pioneering framework called FLea, incorporating the following key components.
  arXiv  Detail & Related papers  (2024-06-13T19:28:08Z)
• An Aggregation-Free Federated Learning for Tackling Data Heterogeneity [50.44021981013037]
  Federated Learning (FL) relies on the effectiveness of utilizing knowledge from distributed datasets. Traditional FL methods adopt an aggregate-then-adapt framework, where clients update local models based on a global model aggregated by the server from the previous training round. We introduce FedAF, a novel aggregation-free FL algorithm.
  arXiv  Detail & Related papers  (2024-04-29T05:55:23Z)
• FLASH: Federated Learning Across Simultaneous Heterogeneities [54.80435317208111]
  FLASH(Federated Learning Across Simultaneous Heterogeneities) is a lightweight and flexible client selection algorithm. It outperforms state-of-the-art FL frameworks under extensive sources of Heterogeneities. It achieves substantial and consistent improvements over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2024-02-13T20:04:39Z)
• Tackling Intertwined Data and Device Heterogeneities in Federated Learning with Unlimited Staleness [4.9851737525099225]
  Federated Learning can be affected by data and device heterogeneities, caused by clients' different local data distributions and latencies in uploading model updates.<n>We present a new FL framework that ensures the accuracy and computational efficiency of this conversion.
  arXiv  Detail & Related papers  (2023-09-24T03:19:40Z)
• Analysis and Optimization of Wireless Federated Learning with Data Heterogeneity [72.85248553787538]
  This paper focuses on performance analysis and optimization for wireless FL, considering data heterogeneity, combined with wireless resource allocation. We formulate the loss function minimization problem, under constraints on long-term energy consumption and latency, and jointly optimize client scheduling, resource allocation, and the number of local training epochs (CRE) Experiments on real-world datasets demonstrate that the proposed algorithm outperforms other benchmarks in terms of the learning accuracy and energy consumption.
  arXiv  Detail & Related papers  (2023-08-04T04:18:01Z)
• PS-FedGAN: An Efficient Federated Learning Framework Based on Partially Shared Generative Adversarial Networks For Data Privacy [56.347786940414935]
  Federated Learning (FL) has emerged as an effective learning paradigm for distributed computation. This work proposes a novel FL framework that requires only partial GAN model sharing. Named as PS-FedGAN, this new framework enhances the GAN releasing and training mechanism to address heterogeneous data distributions.
  arXiv  Detail & Related papers  (2023-05-19T05:39:40Z)
• FL Games: A Federated Learning Framework for Distribution Shifts [71.98708418753786]
  Federated learning aims to train predictive models for data that is distributed across clients, under the orchestration of a server. We propose FL GAMES, a game-theoretic framework for federated learning that learns causal features that are invariant across clients.
  arXiv  Detail & Related papers  (2022-10-31T22:59:03Z)
• Local Learning Matters: Rethinking Data Heterogeneity in Federated Learning [61.488646649045215]
  Federated learning (FL) is a promising strategy for performing privacy-preserving, distributed learning with a network of clients (i.e., edge devices)
  arXiv  Detail & Related papers  (2021-11-28T19:03:39Z)
• Dynamic Attention-based Communication-Efficient Federated Learning [85.18941440826309]
  Federated learning (FL) offers a solution to train a global machine learning model. FL suffers performance degradation when client data distribution is non-IID. We propose a new adaptive training algorithm $textttAdaFL$ to combat this degradation.
  arXiv  Detail & Related papers  (2021-08-12T14:18:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.