Hydra: Multi-head Low-rank Adaptation for Parameter Efficient Fine-tuning

TL;DR

Hydra introduces a multi-head low-rank adaptation method that combines parallel and sequential branches to enhance parameter-efficient fine-tuning of large models, achieving superior performance across tasks.

Contribution

The paper proposes Hydra, a novel multi-head adapter that integrates parallel and sequential adaptation branches for more expressive and generalizable fine-tuning.

Findings

Hydra outperforms existing methods in efficiency and accuracy.

Empirical analysis confirms the complementary benefits of combined branches.

Extensive experiments validate Hydra's superior adaptability across tasks.

Abstract

The recent surge in large-scale foundation models has spurred the development of efficient methods for adapting these models to various downstream tasks. Low-rank adaptation methods, such as LoRA, have gained significant attention due to their outstanding parameter efficiency and no additional inference latency. This paper investigates a more general form of adapter module based on the analysis that parallel and sequential adaptation branches learn novel and general features during fine-tuning, respectively. The proposed method, named Hydra, due to its multi-head computational branches, combines parallel and sequential branch to integrate capabilities, which is more expressive than existing single branch methods and enables the exploration of a broader range of optimal points in the fine-tuning process. In addition, the proposed adaptation method explicitly leverages the pre-trained weights by performing a linear combination of the pre-trained features. It allows the learned features to have better generalization performance across diverse downstream tasks. Furthermore, we perform a comprehensive analysis of the characteristics of each adaptation branch with empirical evidence. Through an extensive range of experiments, encompassing comparisons and ablation studies, we substantiate the efficiency and demonstrate the superior performance of Hydra. This comprehensive evaluation underscores the potential impact and effectiveness of Hydra in a variety of applications. Our code is available on \url{https://github.com/extremebird/Hydra}