The recent development of Foundation Models (FMs), represented by large language models, vision transformers, and multimodal models, has been making a significant impact on both academia and industry. Compared with small-scale models, FMs have a much stronger demand for high-volume data during the pre-training phase. Although general FMs can be pre-trained on data collected from open sources such as the Internet, domain-specific FMs need proprietary data, posing a practical challenge regarding the amount of data available due to privacy concerns. Federated Learning (FL) is a collaborative learning paradigm that breaks the barrier of data availability from different participants. Therefore, it provides a promising solution to customize and adapt FMs to a wide range of domain-specific tasks using distributed datasets whilst preserving privacy. This survey paper discusses the potentials and challenges of synergizing FL and FMs and summarizes core techniques, future directions, and applications. A periodically updated paper collection on FM-FL is available at https://github.com/lishenghui/awesome-fm-fl.

翻译：以大型语言模型、视觉Transformer和多模态模型为代表的基础模型（FMs）的最新发展，正在对学术界和产业界产生重大影响。与小规模模型相比，FMs在预训练阶段对海量数据的需求更为强烈。尽管通用FMs可以利用从互联网等开放来源收集的数据进行预训练，但领域特定的FMs需要专有数据，这因隐私问题导致可用数据量受限，构成了实际挑战。联邦学习（FL）是一种协作学习范式，它打破了不同参与者之间数据可用性的壁垒。因此，它为利用分布式数据集定制和适配FMs以适用于广泛的领域特定任务，同时保护隐私，提供了一个有前景的解决方案。本综述论文探讨了FL与FMs协同的潜力与挑战，并总结了核心技术、未来方向和应用。关于FM-FL的定期更新的论文列表可在 https://github.com/lishenghui/awesome-fm-fl 获取。