Flashback: Understanding and Mitigating Forgetting in Federated Learning

• URL: http://arxiv.org/abs/2402.05558v1
• Date: Thu, 8 Feb 2024 10:52:37 GMT
• Title: Flashback: Understanding and Mitigating Forgetting in Federated Learning
• Authors: Mohammed Aljahdali, Ahmed M. Abdelmoniem, Marco Canini, Samuel Horv\'ath
• Abstract summary: In Federated Learning (FL), forgetting, or the loss of knowledge across rounds, hampers algorithm convergence. We introduce a metric to measure forgetting granularly, ensuring distinct recognition amid new knowledge acquisition. We propose Flashback, an FL algorithm with a dynamic distillation approach that is used to regularize the local models, and effectively aggregate their knowledge.
• Score: 7.248285042377168
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• 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)
• Federated Learning with Reduced Information Leakage and Computation [17.069452700698047]
  Federated learning (FL) is a distributed learning paradigm that allows multiple decentralized clients to collaboratively learn a common model without sharing local data. This paper introduces Upcycled-FL, a strategy that applies first-order approximation at every even round of model update. Under this strategy, half of the FL updates incur no information leakage and require much less computational and transmission costs.
  arXiv  Detail & Related papers  (2023-10-10T06:22:06Z)
• FedLALR: Client-Specific Adaptive Learning Rates Achieve Linear Speedup for Non-IID Data [54.81695390763957]
  Federated learning is an emerging distributed machine learning method. We propose a heterogeneous local variant of AMSGrad, named FedLALR, in which each client adjusts its learning rate. We show that our client-specified auto-tuned learning rate scheduling can converge and achieve linear speedup with respect to the number of clients.
  arXiv  Detail & Related papers  (2023-09-18T12:35:05Z)
• Momentum Benefits Non-IID Federated Learning Simply and Provably [22.800862422479913]
  Federated learning is a powerful paradigm for large-scale machine learning. FedAvg and SCAFFOLD are two prominent algorithms to address these challenges. This paper explores the utilization of momentum to enhance the performance of FedAvg and SCAFFOLD.
  arXiv  Detail & Related papers  (2023-06-28T18:52:27Z)
• When Do Curricula Work in Federated Learning? [56.88941905240137]
  We find that curriculum learning largely alleviates non-IIDness. The more disparate the data distributions across clients the more they benefit from learning. We propose a novel client selection technique that benefits from the real-world disparity in the clients.
  arXiv  Detail & Related papers  (2022-12-24T11:02:35Z)
• Acceleration of Federated Learning with Alleviated Forgetting in Local Training [61.231021417674235]
  Federated learning (FL) enables distributed optimization of machine learning models while protecting privacy. We propose FedReg, an algorithm to accelerate FL with alleviated knowledge forgetting in the local training stage. Our experiments demonstrate that FedReg not only significantly improves the convergence rate of FL, especially when the neural network architecture is deep.
  arXiv  Detail & Related papers  (2022-03-05T02:31:32Z)
• Towards Federated Learning on Time-Evolving Heterogeneous Data [13.080665001587281]
  Federated Learning (FL) is an emerging learning paradigm that preserves privacy by ensuring client data locality on edge devices. Despite recent research efforts on improving the optimization of heterogeneous data, the impact of time-evolving heterogeneous data in real-world scenarios has not been well studied. We propose Continual Federated Learning (CFL), a flexible framework, to capture the time-evolving heterogeneity of FL.
  arXiv  Detail & Related papers  (2021-12-25T14:58:52Z)
• 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)
• Convergence and Accuracy Trade-Offs in Federated Learning and Meta-Learning [0.0]
  We study a family of algorithms, which we refer to as local update methods. We prove that for quadratic models, local update methods are equivalent to first-order optimization on a surrogate loss. We derive novel convergence rates showcasing these trade-offs and highlight their importance in communication-limited settings.
  arXiv  Detail & Related papers  (2021-03-08T19:40:32Z)
• Straggler-Resilient Federated Learning: Leveraging the Interplay Between Statistical Accuracy and System Heterogeneity [57.275753974812666]
  Federated learning involves learning from data samples distributed across a network of clients while the data remains local. In this paper, we propose a novel straggler-resilient federated learning method that incorporates statistical characteristics of the clients' data to adaptively select the clients in order to speed up the learning procedure.
  arXiv  Detail & Related papers  (2020-12-28T19:21:14Z)

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.