Jointly Exploring Client Drift and Catastrophic Forgetting in Dynamic Learning

• URL: http://arxiv.org/abs/2309.00688v1
• Date: Fri, 1 Sep 2023 18:14:30 GMT
• Title: Jointly Exploring Client Drift and Catastrophic Forgetting in Dynamic Learning
• Authors: Niklas Babendererde, Moritz Fuchs, Camila Gonzalez, Yuri Tolkach, Anirban Mukhopadhyay
• Abstract summary: Client Drift and Catastrophic Forgetting are fundamental obstacles to guaranteeing consistent performance. We propose a unified framework for building a controlled test environment for Client Drift and Catastrophic Forgetting. We show that a combination of moderate Client Drift and Catastrophic Forgetting can even improve the performance of the resulting model.
• Score: 1.0808810256442274
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Federated and Continual Learning have emerged as potential paradigms for the robust and privacy-aware use of Deep Learning in dynamic environments. However, Client Drift and Catastrophic Forgetting are fundamental obstacles to guaranteeing consistent performance. Existing work only addresses these problems separately, which neglects the fact that the root cause behind both forms of performance deterioration is connected. We propose a unified analysis framework for building a controlled test environment for Client Drift -- by perturbing a defined ratio of clients -- and Catastrophic Forgetting -- by shifting all clients with a particular strength. Our framework further leverages this new combined analysis by generating a 3D landscape of the combined performance impact from both. We demonstrate that the performance drop through Client Drift, caused by a certain share of shifted clients, is correlated to the drop from Catastrophic Forgetting resulting from a corresponding shift strength. Correlation tests between both problems for Computer Vision (CelebA) and Medical Imaging (PESO) support this new perspective, with an average Pearson rank correlation coefficient of over 0.94. Our framework's novel ability of combined spatio-temporal shift analysis allows us to investigate how both forms of distribution shift behave in mixed scenarios, opening a new pathway for better generalization. We show that a combination of moderate Client Drift and Catastrophic Forgetting can even improve the performance of the resulting model (causing a "Generalization Bump") compared to when only one of the shifts occurs individually. We apply a simple and commonly used method from Continual Learning in the federated setting and observe this phenomenon to be reoccurring, leveraging the ability of our framework to analyze existing and novel methods for Federated and Continual Learning.

Related papers

• The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective [12.916988821333124]
  In federated learning (FL), model aggregation is a critical step by which multiple clients share their knowledge with one another. This temporary performance drop can potentially slow down the convergence of the FL model. We propose several simple yet effective strategies to mitigate the negative impacts of model aggregation.
  arXiv  Detail & Related papers  (2025-02-05T14:45:56Z)
• FedCAda: Adaptive Client-Side Optimization for Accelerated and Stable Federated Learning [57.38427653043984]
  Federated learning (FL) has emerged as a prominent approach for collaborative training of machine learning models across distributed clients. We introduce FedCAda, an innovative federated client adaptive algorithm designed to tackle this challenge. We demonstrate that FedCAda outperforms the state-of-the-art methods in terms of adaptability, convergence, stability, and overall performance.
  arXiv  Detail & Related papers  (2024-05-20T06:12:33Z)
• Scalable Federated Unlearning via Isolated and Coded Sharding [76.12847512410767]
  Federated unlearning has emerged as a promising paradigm to erase the client-level data effect. This paper proposes a scalable federated unlearning framework based on isolated sharding and coded computing.
  arXiv  Detail & Related papers  (2024-01-29T08:41:45Z)
• Relaxed Contrastive Learning for Federated Learning [48.96253206661268]
  We propose a novel contrastive learning framework to address the challenges of data heterogeneity in federated learning. Our framework outperforms all existing federated learning approaches by huge margins on the standard benchmarks.
  arXiv  Detail & Related papers  (2024-01-10T04:55:24Z)
• 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)
• Combating Exacerbated Heterogeneity for Robust Models in Federated Learning [91.88122934924435]
  Combination of adversarial training and federated learning can lead to the undesired robustness deterioration. We propose a novel framework called Slack Federated Adversarial Training (SFAT) We verify the rationality and effectiveness of SFAT on various benchmarked and real-world datasets.
  arXiv  Detail & Related papers  (2023-03-01T06:16:15Z)
• Federated Learning under Heterogeneous and Correlated Client Availability [10.05687757555923]
  This paper presents the first convergence analysis for a FedAvg-like FL algorithm under heterogeneous and correlated client availability. We propose CA-Fed, a new FL algorithm that tries to balance the conflicting goals of maximizing convergence speed and minimizing model bias. Our experimental results show that CA-Fed achieves higher time-average accuracy and a lower standard deviation than state-of-the-art AdaFed and F3AST.
  arXiv  Detail & Related papers  (2023-01-11T18:38:48Z)
• 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)
• DRFLM: Distributionally Robust Federated Learning with Inter-client Noise via Local Mixup [58.894901088797376]
  federated learning has emerged as a promising approach for training a global model using data from multiple organizations without leaking their raw data. We propose a general framework to solve the above two challenges simultaneously. We provide comprehensive theoretical analysis including robustness analysis, convergence analysis, and generalization ability.
  arXiv  Detail & Related papers  (2022-04-16T08:08:29Z)
• Addressing Client Drift in Federated Continual Learning with Adaptive Optimization [10.303676184878896]
  We outline a framework for performing Federated Continual Learning (FCL) by using NetTailor as a candidate continual learning approach. We show that adaptive federated optimization can reduce the adverse impact of client drift and showcase its effectiveness on CIFAR100, MiniImagenet, and Decathlon benchmarks.
  arXiv  Detail & Related papers  (2022-03-24T20:00:03Z)

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.