针对小规模用户个性化需求，提出双层聚合的联邦微调方法。
Bi-level Personalization for Federated Foundation Models: A Task-vector Aggregation Approach
- 客户端用私有数据做个性化微调，服务器用任务向量聚类相似用户。
- 在多个基准数据集上验证有效，提升小样本场景下的模型性能。
- 适合数据异构、用户少但需个性化服务的联邦学习场景。
联邦基础模型代表了一种新的联合微调预训练基础模型的范式。然而，在新用户或特定场景下进行微调仍具挑战性，因为这些场景的数据量远小于预训练阶段的大规模数据。在此背景下，个性化与联邦之间的权衡更加敏感。为此，我们提出一种用于联邦基础模型微调的双层个性化框架。具体而言，首先在客户端使用其私有数据进行个性化微调，然后在服务器端基于客户端特定的任务向量测量相似用户，进行个性化聚合。利用客户端微调获得的个性化信息，服务器端的个性化聚合能够在保持群体个性化的同时，缓解非独立同分布（non-IID）数据下无关或兴趣冲突客户端的干扰。大量实验分析证明了所提算法在基准数据集上的有效性。
原文摘要 · Abstract (English)
Federated foundation models represent a new paradigm to jointly fine-tune pre-trained foundation models across clients. It is still a challenge to fine-tune foundation models for a small group of new users or specialized scenarios, which typically involve limited data compared to the large-scale data used in pre-training. In this context, the trade-off between personalization and federation becomes more sensitive. To tackle these, we proposed a bi-level personalization framework for federated fine-tuning on foundation models. Specifically, we conduct personalized fine-tuning on the client-level using its private data, and then conduct a personalized aggregation on the server-level using similar users measured by client-specific task vectors. Given the personalization information gained from client-level fine-tuning, the server-level personalized aggregation can gain group-wise personalization information while mitigating the disturbance of irrelevant or interest-conflict clients with non-IID data. The effectiveness of the proposed algorithm has been demonstrated by extensive experimental analysis in benchmark datasets.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。