Abstract
Prompt tuning is a parameter-efficient method, which learns soft prompts and conditions frozen language models to perform specific downstream tasks. Though effective, prompt tuning under few-shot settings on the one hand heavily relies on a good initialization of soft prompts. On the other hand, it can easily result in overfitting. Existing works leverage pre-training or supervised meta-learning to initialize soft prompts but they cannot data-efficiently generalize to unseen downstream tasks. To address the above problems, this paper proposes a novel Self-sUpervised meta-Prompt learning framework with meta-gradient Regularization for few-shot generalization (SUPMER). We first design a set of self-supervised anchor meta-training tasks with different task formats and further enrich the task distribution with curriculum-based task augmentation. Then a novel meta-gradient regularization method is integrated into meta-prompt learning. It meta-learns to transform the raw gradients during few-shot learning into a domain-generalizable direction, thus alleviating the problem of overfitting. Extensive experiments show that SUPMER achieves better performance for different few-shot downstream tasks, and also exhibits a stronger domain generalization ability.
Abstract (translated)
Prompt Tuner是一种参数高效的方法,通过学习软提示和冻结语言模型来执行特定的后续任务。尽管这种方法很有效,但是在单样本设置下,它很大程度上依赖于良好的软提示初始化。另一方面,它很容易导致过拟合。现有的工作利用预训练或监督的元学习初始化软提示,但它们无法高效地从未见过的后续任务中泛化数据。为了解决这些问题,本文提出了一种 novel 的自我监督元-Prompt learning框架和元梯度 Regularization,用于单样本 generalization (SUPMER)。我们首先设计了一系列不同的任务格式的自我监督基准元-训练任务,并使用课程增强任务扩展任务分布,进一步丰富了任务分布。然后,我们引入了一种新的元梯度 Regularization方法,并在元-Prompt learning中集成它,在单样本学习中将原始梯度转换为域通用的方向,从而减轻过拟合的问题。广泛的实验结果表明,SUPMER在不同单样本后续任务中取得了更好的表现,同时也表现出更强的域通用能力。
URL
https://arxiv.org/abs/2303.12314