Federated learning (FL) is a hot collaborative training framework via aggregating model parameters of decentralized local clients. However, most FL methods unreasonably assume data categories of FL framework are known and fixed in advance. Moreover, some new local clients that collect novel categories unseen by other clients may be introduced to FL training irregularly. These issues render global model to undergo catastrophic forgetting on old categories, when local clients receive new categories consecutively under limited memory of storing old categories. To tackle the above issues, we propose a novel Local-Global Anti-forgetting (LGA) model. It ensures no local clients are left behind as they learn new classes continually, by addressing local and global catastrophic forgetting. Specifically, considering tackling class imbalance of local client to surmount local forgetting, we develop a category-balanced gradient-adaptive compensation loss and a category gradient-induced semantic distillation loss. They can balance heterogeneous forgetting speeds of hard-to-forget and easy-to-forget old categories, while ensure consistent class-relations within different tasks. Moreover, a proxy server is designed to tackle global forgetting caused by Non-IID class imbalance between different clients. It augments perturbed prototype images of new categories collected from local clients via self-supervised prototype augmentation, thus improving robustness to choose the best old global model for local-side semantic distillation loss. Experiments on representative datasets verify superior performance of our model against comparison methods. The code is available at https://github.com/JiahuaDong/LGA.

翻译：联邦学习（FL）是一种通过聚合分散局部客户端模型参数实现协同训练的热门框架。然而，大多数FL方法不合理地假设联邦学习框架的数据类别事先已知且固定不变。此外，部分采集其他客户端未曾见过的新类别数据的局部客户端可能会不规则地加入联邦学习训练。当局部客户端在存储旧类别数据的有限内存限制下连续接收新类别时，这些问题会导致全局模型在旧类别上发生灾难性遗忘。为解决上述问题，我们提出一种新颖的局部-全局抗遗忘（LGA）模型。该模型通过应对局部和全局灾难性遗忘，确保各局部客户端在持续学习新类别时无一掉队。具体而言，针对局部客户端类别不平衡问题以克服局部遗忘，我们设计了类别平衡的梯度自适应补偿损失与类别梯度诱导语义蒸馏损失。这两项损失能平衡难遗忘与易遗忘旧类别的异构遗忘速度，同时确保不同任务间的类间关系保持一致。此外，我们开发了代理服务器以应对客户端间非独立同分布类别不平衡导致的全局遗忘问题。该服务器通过自监督原型增强手段扩充从局部客户端采集的新类别受扰动原型图像，从而提升为局部端语义蒸馏损失选择最优旧全局模型的鲁棒性。在代表性数据集上的实验证明，我们的模型相较于对比方法具有更优性能。代码已开源至https://github.com/JiahuaDong/LGA。