Federated Low-Rank Adaptation for Foundation Models: A Survey

TL;DR

This survey reviews how Low-Rank Adaptation (LoRA) is integrated into federated learning for foundation models, addressing key challenges like privacy, heterogeneity, and efficiency, and discusses future research directions.

Contribution

It categorizes existing FedLoRA methods, analyzes challenges, and outlines future research avenues in federated low-rank adaptation for foundation models.

Findings

LoRA reduces training parameters significantly.

Federated learning enables privacy-preserving model fine-tuning.

Current methods face challenges in heterogeneity and efficiency.

Abstract

Effectively leveraging private datasets remains a significant challenge in developing foundation models. Federated Learning (FL) has recently emerged as a collaborative framework that enables multiple users to fine-tune these models while mitigating data privacy risks. Meanwhile, Low-Rank Adaptation (LoRA) offers a resource-efficient alternative for fine-tuning foundation models by dramatically reducing the number of trainable parameters. This survey examines how LoRA has been integrated into federated fine-tuning for foundation models, an area we term FedLoRA, by focusing on three key challenges: distributed learning, heterogeneity, and efficiency. We further categorize existing work based on the specific methods used to address each challenge. Finally, we discuss open research questions and highlight promising directions for future investigation, outlining the next steps for advancing FedLoRA.