Scattered or Connected? An Optimized Parameter-efficient Tuning Approach for Information Retrieval

TL;DR

This paper investigates parameter-efficient tuning methods for information retrieval, identifies their limitations, and proposes a new connected module approach that improves training stability and performance, matching or surpassing full fine-tuning.

Contribution

It introduces a novel module connection technique for parameter-efficient tuning in IR, enhancing training stability and achieving competitive results with full fine-tuning.

Findings

Existing methods underperform when updating less than 1% of parameters.

The proposed connected modules improve training stability.

Our method outperforms existing approaches and matches full fine-tuning results.

Abstract

Pre-training and fine-tuning have achieved significant advances in the information retrieval (IR). A typical approach is to fine-tune all the parameters of large-scale pre-trained models (PTMs) on downstream tasks. As the model size and the number of tasks increase greatly, such approach becomes less feasible and prohibitively expensive. Recently, a variety of parameter-efficient tuning methods have been proposed in natural language processing (NLP) that only fine-tune a small number of parameters while still attaining strong performance. Yet there has been little effort to explore parameter-efficient tuning for IR. In this work, we first conduct a comprehensive study of existing parameter-efficient tuning methods at both the retrieval and re-ranking stages. Unlike the promising results in NLP, we find that these methods cannot achieve comparable performance to full fine-tuning at both stages when updating less than 1\% of the original model parameters. More importantly, we find that the existing methods are just parameter-efficient, but not learning-efficient as they suffer from unstable training and slow convergence. To analyze the underlying reason, we conduct a theoretical analysis and show that the separation of the inserted trainable modules makes the optimization difficult. To alleviate this issue, we propose to inject additional modules alongside the \acp{PTM} to make the original scattered modules connected. In this way, all the trainable modules can form a pathway to smooth the loss surface and thus help stabilize the training process. Experiments at both retrieval and re-ranking stages show that our method outperforms existing parameter-efficient methods significantly, and achieves comparable or even better performance over full fine-tuning.