联邦持续学习走向在线：面向视觉任务及其他领域的不确定性感知记忆管理
Federated Continual Learning Goes Online: Uncertainty-Aware Memory Management for Vision Tasks and Beyond
AI总结：
针对联邦持续学习中的灾难性遗忘问题，提出一种基于Bregman信息的不确定性感知记忆管理方法，适用于在线流式数据场景，可处理多种模态，在保持数据机密性和通信效率的同时有效减少遗忘。
摘要：
鉴于能够对更真实和动态的问题进行建模，联邦持续学习（FCL）近年来受到越来越多的研究关注。在此设置中遇到的一个众所周知的问题是所谓的灾难性遗忘，即学习模型倾向于关注较新的任务，而忘记先前学到的知识。目前大多数FCL方法提出基于生成式的解决方案来解决该问题。然而，这种设置需要对数据进行多个训练轮次，这意味着一种离线设置，其中数据集存储在本地并随时间保持不变。此外，所提出的解决方案仅针对视觉任务。为克服这些局限性，我们提出了一种新方法，以处理在线场景中的不同模态，其中新数据以只能处理一次的小批量流形式到达。为解决灾难性遗忘，我们提出了一种基于不确定性感知的记忆方法。具体来说，我们建议使用基于Bregman信息（BI）的估计器来计算模型在样本级别的方差。通过预测不确定性的度量，我们检索具有特定特征的样本，并通过在这些样本上重新训练模型，我们展示了该方法在现实设置中减少遗忘效应的潜力，同时与最先进的方法相比，保持了数据机密性和具有竞争力的通信效率。
英文摘要：
Given the ability to model more realistic and dynamic problems, Federated Continual Learning (FCL) has been increasingly investigated recently. A well-known problem encountered in this setting is the so-called catastrophic forgetting, for which the learning model is inclined to focus on more recent tasks while forgetting the previously learned knowledge. The majority of the current approaches in FCL propose generative-based solutions to solve said problem. However, this setting requires multiple training epochs over the data, implying an offline setting where datasets are stored locally and remain unchanged over time. Furthermore, the proposed solutions are tailored for vision tasks solely. To overcome these limitations, we propose a new approach to deal with different modalities in the online scenario where new data arrive in streams of mini-batches that can only be processed once. To solve catastrophic forgetting, we propose an uncertainty-aware memory-based approach. Specifically, we suggest using an estimator based on the Bregman Information (BI) to compute the model's variance at the sample level. Through measures of predictive uncertainty, we retrieve samples with specific characteristics, and - by retraining the model on such samples - we demonstrate the potential of this approach to reduce the forgetting effect in realistic settings while maintaining data confidentiality and competitive communication efficiency compared to state-of-the-art approaches.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
