Federated Foundation Models (FedFMs) represent a distributed learning paradigm that fuses general competences of foundation models as well as privacy-preserving capabilities of federated learning. This combination allows the large foundation models and the small local domain models at the remote clients to learn from each other in a teacher-student learning setting. This paper provides a comprehensive summary of the ten challenging problems inherent in FedFMs, encompassing foundational theory, utilization of private data, continual learning, unlearning, Non-IID and graph data, bidirectional knowledge transfer, incentive mechanism design, game mechanism design, model watermarking, and efficiency. The ten challenging problems manifest in five pivotal aspects: ``Foundational Theory," which aims to establish a coherent and unifying theoretical framework for FedFMs. ``Data," addressing the difficulties in leveraging domain-specific knowledge from private data while maintaining privacy; ``Heterogeneity," examining variations in data, model, and computational resources across clients; ``Security and Privacy," focusing on defenses against malicious attacks and model theft; and ``Efficiency," highlighting the need for improvements in training, communication, and parameter efficiency. For each problem, we offer a clear mathematical definition on the objective function, analyze existing methods, and discuss the key challenges and potential solutions. This in-depth exploration aims to advance the theoretical foundations of FedFMs, guide practical implementations, and inspire future research to overcome these obstacles, thereby enabling the robust, efficient, and privacy-preserving FedFMs in various real-world applications.
View on arXiv@article{fan2025_2502.12176,
title={ Ten Challenging Problems in Federated Foundation Models },
author={ Tao Fan and Hanlin Gu and Xuemei Cao and Chee Seng Chan and Qian Chen and Yiqiang Chen and Yihui Feng and Yang Gu and Jiaxiang Geng and Bing Luo and Shuoling Liu and Win Kent Ong and Chao Ren and Jiaqi Shao and Chuan Sun and Xiaoli Tang and Hong Xi Tae and Yongxin Tong and Shuyue Wei and Fan Wu and Wei Xi and Mingcong Xu and He Yang and Xin Yang and Jiangpeng Yan and Hao Yu and Han Yu and Teng Zhang and Yifei Zhang and Xiaojin Zhang and Zhenzhe Zheng and Lixin Fan and Qiang Yang },
journal={arXiv preprint arXiv:2502.12176},
year={ 2025 }
}