Robust Federated Finetuning of Foundation Models via Alternating Minimization of LoRA
This addresses communication efficiency and data heterogeneity challenges in federated learning for foundation models, representing an incremental improvement over existing PEFT methods.
The paper tackles the problem of federated fine-tuning of foundation models with limited communication and heterogeneous data by introducing RoLoRA, a framework using alternating minimization for LoRA. Results show RoLoRA provides communication benefits and substantially enhances robustness and effectiveness in multiple federated fine-tuning scenarios.
Parameter-Efficient Fine-Tuning (PEFT) has risen as an innovative training strategy that updates only a select few model parameters, significantly lowering both computational and memory demands. PEFT also helps to decrease data transfer in federated learning settings, where communication depends on the size of updates. In this work, we explore the constraints of previous studies that integrate a well-known PEFT method named LoRA with federated fine-tuning, then introduce RoLoRA, a robust federated fine-tuning framework that utilizes an alternating minimization approach for LoRA, providing greater robustness against decreasing fine-tuning parameters and increasing data heterogeneity. Our results indicate that RoLoRA not only presents the communication benefits but also substantially enhances the robustness and effectiveness in multiple federated fine-tuning scenarios.