Foundation Models (FMs) such as GPT-4 encoded with vast knowledge and powerful emergent abilities have achieved remarkable success in various natural language processing and computer vision tasks. Grounding FMs by adapting them to domain-specific tasks or augmenting them with domain-specific knowledge enables us to exploit the full potential of FMs. However, grounding FMs faces several challenges, stemming primarily from constrained computing resources, data privacy, model heterogeneity, and model ownership. Federated Transfer Learning (FTL), the combination of federated learning and transfer learning, provides promising solutions to address these challenges. In recent years, the need for grounding FMs leveraging FTL, coined FTL-FM, has arisen strongly in both academia and industry. Motivated by the strong growth in FTL-FM research and the potential impact of FTL-FM on industrial applications, we propose an FTL-FM framework that formulates problems of grounding FMs in the federated learning setting, construct a detailed taxonomy based on the FTL-FM framework to categorize state-of-the-art FTL-FM works, and comprehensively overview FTL-FM works based on the proposed taxonomy. We also establish correspondences between FTL-FM and conventional phases of adapting FM so that FM practitioners can align their research works with FTL-FM. In addition, we overview advanced efficiency-improving and privacy-preserving techniques because efficiency and privacy are critical concerns in FTL-FM. Last, we discuss opportunities and future research directions of FTL-FM.

翻译：基础模型（如GPT-4）凭借其编码的海量知识与涌现的强大能力，已在自然语言处理和计算机视觉任务中取得显著成功。通过将基础模型适配到特定领域任务或增强领域知识进行落地，能够充分挖掘基础模型的潜力。然而，基础模型的落地面临计算资源受限、数据隐私、模型异构性和模型所有权等多重挑战。联邦迁移学习作为联邦学习与迁移学习的结合，为解决这些挑战提供了可行方案。近年来，利用联邦迁移学习落地基础模型的需求（称为FTL-FM）在学术界和工业界日益凸显。基于FTL-FM研究的迅猛发展及其对工业应用的潜在影响，本文提出一个FTL-FM框架，系统阐述了联邦学习场景中基础模型落地的核心问题，构建了基于该框架的详细分类体系以梳理现有FTL-FM前沿工作，并依据所提分类法对这些工作进行了全面综述。同时，我们建立了FTL-FM与传统基础模型适配阶段之间的对应关系，使基础模型从业者能够将其研究工作与FTL-FM对齐。此外，针对FTL-FM中关键的效率与隐私问题，我们综述了先进的效率提升与隐私保护技术。最后，探讨了FTL-FM的发展机遇与未来研究方向。