Accurate Forgetting for Heterogeneous Federated Continual Learning

• URL: http://arxiv.org/abs/2502.14205v1
• Date: Thu, 20 Feb 2025 02:35:17 GMT
• Title: Accurate Forgetting for Heterogeneous Federated Continual Learning
• Authors: Abudukelimu Wuerkaixi, Sen Cui, Jingfeng Zhang, Kunda Yan, Bo Han, Gang Niu, Lei Fang, Changshui Zhang, Masashi Sugiyama,
• Abstract summary: We propose a new concept accurate forgetting (AF) and develop a novel generative-replay methodMethodwhich selectively utilizes previous knowledge in federated networks. We employ a probabilistic framework based on a normalizing flow model to quantify the credibility of previous knowledge.
• Score: 89.08735771893608
• License:
• Abstract: Recent years have witnessed a burgeoning interest in federated learning (FL). However, the contexts in which clients engage in sequential learning remain under-explored. Bridging FL and continual learning (CL) gives rise to a challenging practical problem: federated continual learning (FCL). Existing research in FCL primarily focuses on mitigating the catastrophic forgetting issue of continual learning while collaborating with other clients. We argue that the forgetting phenomena are not invariably detrimental. In this paper, we consider a more practical and challenging FCL setting characterized by potentially unrelated or even antagonistic data/tasks across different clients. In the FL scenario, statistical heterogeneity and data noise among clients may exhibit spurious correlations which result in biased feature learning. While existing CL strategies focus on a complete utilization of previous knowledge, we found that forgetting biased information is beneficial in our study. Therefore, we propose a new concept accurate forgetting (AF) and develop a novel generative-replay method~\method~which selectively utilizes previous knowledge in federated networks. We employ a probabilistic framework based on a normalizing flow model to quantify the credibility of previous knowledge. Comprehensive experiments affirm the superiority of our method over baselines.

Related papers

• Flashback: Understanding and Mitigating Forgetting in Federated Learning [7.248285042377168]
  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.
  arXiv  Detail & Related papers  (2024-02-08T10:52:37Z)
• Federated Learning Can Find Friends That Are Advantageous [14.993730469216546]
  In Federated Learning (FL), the distributed nature and heterogeneity of client data present both opportunities and challenges. We introduce a novel algorithm that assigns adaptive aggregation weights to clients participating in FL training, identifying those with data distributions most conducive to a specific learning objective.
  arXiv  Detail & Related papers  (2024-02-07T17:46:37Z)
• Few-Shot Class-Incremental Learning with Prior Knowledge [94.95569068211195]
  We propose Learning with Prior Knowledge (LwPK) to enhance the generalization ability of the pre-trained model. Experimental results indicate that LwPK effectively enhances the model resilience against catastrophic forgetting.
  arXiv  Detail & Related papers  (2024-02-02T08:05:35Z)
• Continual Learning with Pre-Trained Models: A Survey [61.97613090666247]
  Continual Learning aims to overcome the catastrophic forgetting of former knowledge when learning new ones. This paper presents a comprehensive survey of the latest advancements in PTM-based CL.
  arXiv  Detail & Related papers  (2024-01-29T18:27:52Z)
• Federated Continual Learning via Knowledge Fusion: A Survey [33.74289759536269]
  Federated Continual Learning (FCL) is an emerging paradigm to address model learning in both federated and continual learning environments. The key objective of FCL is to fuse heterogeneous knowledge from different clients and retain knowledge of previous tasks while learning on new ones. In this work, we delineate federated learning and continual learning first and then discuss their integration, i.e., FCL, and particular FCL via knowledge fusion.
  arXiv  Detail & Related papers  (2023-12-27T08:47:39Z)
• Continual Learning in the Presence of Spurious Correlation [23.999136417157597]
  We show that standard continual learning algorithms can transfer biases from one task to another, both forward and backward. We propose a plug-in method for debiasing-aware continual learning, dubbed as Group-class Balanced Greedy Sampling (BGS)
  arXiv  Detail & Related papers  (2023-03-21T14:06:12Z)
• 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)
• Towards Federated Long-Tailed Learning [76.50892783088702]
  Data privacy and class imbalance are the norm rather than the exception in many machine learning tasks. Recent attempts have been launched to, on one side, address the problem of learning from pervasive private data, and on the other side, learn from long-tailed data. This paper focuses on learning with long-tailed (LT) data distributions under the context of the popular privacy-preserved federated learning (FL) framework.
  arXiv  Detail & Related papers  (2022-06-30T02:34:22Z)
• 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)

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.