Deep learning models are prone to forgetting information learned in the past when trained on new data. This problem becomes even more pronounced in the context of federated learning (FL), where data is decentralized and subject to independent changes for each user. Continual Learning (CL) studies this so-called \textit{catastrophic forgetting} phenomenon primarily in centralized settings, where the learner has direct access to the complete training dataset. However, applying CL techniques to FL is not straightforward due to privacy concerns and resource limitations. This paper presents a framework for federated class incremental learning that utilizes a generative model to synthesize samples from past distributions instead of storing part of past data. Then, clients can leverage the generative model to mitigate catastrophic forgetting locally. The generative model is trained on the server using data-free methods at the end of each task without requesting data from clients. Therefore, it reduces the risk of data leakage as opposed to training it on the client's private data. We demonstrate significant improvements for the CIFAR-100 dataset compared to existing baselines.

翻译：深度学习模型在训练新数据时容易遗忘过去学到的信息。这一问题在联邦学习（FL）背景下尤为突出，其中数据是去中心化的且每位用户的数据会独立发生变化。持续学习（CL）主要研究这种所谓的“灾难性遗忘”现象，其场景通常是集中式环境，学习者可以直接访问完整的训练数据集。然而，由于隐私问题和资源限制，将CL技术应用于FL并非易事。本文提出了一种联邦类增量学习框架，该框架利用生成模型从过去分布中合成样本，而非存储部分过往数据。随后，客户端可利用该生成模型在本地缓解灾难性遗忘。该生成模型在服务器端采用无数据方法进行训练，且在每个任务结束时无需从客户端请求数据。因此，与在客户端私有数据上训练相比，它降低了数据泄露的风险。实验表明，与现有基线方法相比，该方法在CIFAR-100数据集上取得了显著改进。