DePT: Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning

TL;DR

DePT introduces a decomposed prompt tuning method that reduces memory and time costs while improving performance in parameter-efficient fine-tuning for large language and vision-language models.

Contribution

DePT decomposes soft prompts into shorter prompts and low-rank matrices, enhancing efficiency without increasing trainable parameters.

Findings

Outperforms state-of-the-art PEFT methods on 23 NLP and VL tasks.

More efficient as model size increases.

Seamlessly integrates with few-shot learning and various architectures.

Abstract

Prompt tuning (PT), where a small amount of trainable soft (continuous) prompt vectors is affixed to the input of language models (LM), has shown promising results across various tasks and models for parameter-efficient fine-tuning (PEFT). PT stands out from other PEFT approaches because it maintains competitive performance with fewer trainable parameters and does not drastically scale up its parameters as the model size expands. However, PT introduces additional soft prompt tokens, leading to longer input sequences, which significantly impacts training and inference time and memory usage due to the Transformer's quadratic complexity. Particularly concerning for Large Language Models (LLMs) that face heavy daily querying. To address this issue, we propose Decomposed Prompt Tuning (DePT), which decomposes the soft prompt into a shorter soft prompt and a pair of low-rank matrices that are then optimised with two different learning rates. This allows DePT to achieve better performance while saving substantial memory and time costs compared to vanilla PT and its variants, without changing trainable parameter sizes. Through extensive experiments on 23 natural language processing (NLP) and vision-language (VL) tasks, we demonstrate that DePT outperforms state-of-the-art PEFT approaches, including the full fine-tuning baseline, in some scenarios. Additionally, we empirically show that DEPT grows more efficient as the model size increases. Our further study reveals that DePT integrates seamlessly with parameter-efficient transfer learning in the few-shot learning setting and highlights its adaptability to various model architectures and sizes.