Existing federated learning methods have effectively addressed decentralized learning in scenarios involving data privacy and non-IID data. However, in real-world situations, each client dynamically learns new classes, requiring the global model to maintain discriminative capabilities for both new and old classes. To effectively mitigate the effects of catastrophic forgetting and data heterogeneity under low communication costs, we designed a simple and effective method named PLoRA. On the one hand, we adopt prototype learning to learn better feature representations and leverage the heuristic information between prototypes and class features to design a prototype re-weight module to solve the classifier bias caused by data heterogeneity without retraining the classification layer. On the other hand, our approach utilizes a pre-trained model as the backbone and utilizes LoRA to fine-tune with a tiny amount of parameters when learning new classes. Moreover, PLoRA does not rely on similarity-based module selection strategies, thereby further reducing communication overhead. Experimental results on standard datasets indicate that our method outperforms the state-of-the-art approaches significantly. More importantly, our method exhibits strong robustness and superiority in various scenarios and degrees of data heterogeneity. Our code will be publicly available.

翻译：现有联邦学习方法已有效解决了涉及数据隐私和非独立同分布数据场景下的分散式学习问题。然而在真实场景中，每个客户端会动态学习新类别，这就要求全局模型能同时保持对新旧类别的判别能力。为在低通信成本下有效缓解灾难性遗忘和数据异质性的影响，我们设计了一种名为PLoRA的简洁有效方法。一方面，我们采用原型学习以获得更优的特征表示，并利用原型与类别特征之间的启发式信息设计原型重加权模块，无需重新训练分类层即可解决数据异质性导致的分类器偏差问题。另一方面，该方法以预训练模型作为主干网络，在学习新类别时通过LoRA仅微调极少参数。此外，PLoRA不依赖基于相似度的模块选择策略，从而进一步降低通信开销。在标准数据集上的实验结果表明，我们的方法显著优于当前最优方法。更重要的是，该方法在多种场景及不同数据异质性程度下均展现出强大的鲁棒性和优越性。我们将公开相关代码。