从基础模型中探索语义属性用于不相交标签空间的联邦学习
Exploring Semantic Attributes from A Foundation Model for Federated Learning of Disjoint Label Spaces
AI总结：
本文提出联邦零样本学习范式，通过传递隐私保护性更强的中层语义属性知识并引入外部语义增强，在多个非共享数据客户端上学习并聚合全局可泛化模型，实验验证了其有效性。
摘要：
当来自不同来源的数据因数据隐私或传输限制而无法共享时，传统的集中式深度学习范式不可行。为解决这一问题，联邦学习被引入，以在多个具有非共享数据的来源（客户端）之间传递知识，同时优化一个全局泛化的中心模型（服务器）。现有的联邦学习范式大多侧重于在模型之间传递整体性高层知识（如类别），这些知识与特定感兴趣对象密切相关，因此可能遭受逆向攻击。相比之下，在本工作中，我们考虑传递中层语义知识（如属性），这类知识对特定感兴趣对象不敏感，因此更具隐私保护性和可扩展性。为此，我们提出了一种新的联邦零样本学习（Federated Zero-Shot Learning, FZSL）范式，在多个具有非共享本地数据的本地客户端上学习中层语义知识，并累积聚合一个全局泛化的中心模型以供部署。为了提高模型的判别能力，我们提出从外部知识中探索语义知识增强，以丰富FZSL中的中层语义空间。在五个零样本学习基准数据集上的大量实验验证了我们的方法在通过中层语义知识迁移优化可泛化联邦学习模型方面的有效性。
英文摘要：
Conventional centralised deep learning paradigms are not feasible when data from different sources cannot be shared due to data privacy or transmission limitation. To resolve this problem, federated learning has been introduced to transfer knowledge across multiple sources (clients) with non-shared data while optimising a globally generalised central model (server). Existing federated learning paradigms mostly focus on transferring holistic high-level knowledge (such as class) across models, which are closely related to specific objects of interest so may suffer from inverse attack. In contrast, in this work, we consider transferring mid-level semantic knowledge (such as attribute) which is not sensitive to specific objects of interest and therefore is more privacy-preserving and scalable. To this end, we formulate a new Federated Zero-Shot Learning (FZSL) paradigm to learn mid-level semantic knowledge at multiple local clients with non-shared local data and cumulatively aggregate a globally generalised central model for deployment. To improve model discriminative ability, we propose to explore semantic knowledge augmentation from external knowledge for enriching the mid-level semantic space in FZSL. Extensive experiments on five zeroshot learning benchmark datasets validate the effectiveness of our approach for optimising a generalisable federated learning model with mid-level semantic knowledge transfer.
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。
