Exploring Universal Intrinsic Task Subspace via Prompt Tuning
Why can pre-trained language models (PLMs) learn universal representations and effectively adapt to broad NLP tasks differing a lot superficially? In this work, we empirically find evidence indicating that the adaptations of PLMs to various few-shot tasks can be reparameterized as optimizing only a few free parameters in a unified low-dimensional intrinsic task subspace, which may help us understand why PLMs could easily adapt to various NLP tasks with small-scale data. To find such a subspace and examine its universality, we propose an analysis pipeline called intrinsic prompt tuning (IPT). Specifically, we resort to the recent success of prompt tuning and decompose the soft prompts of multiple NLP tasks into the same low-dimensional nonlinear subspace, then we learn to adapt the PLM to unseen data or tasks by only tuning parameters in this subspace. In the experiments, we study diverse few-shot NLP tasks and surprisingly find that in a 250-dimensional subspace found with 100 tasks, by only tuning 250 free parameters, we can recover 97% and 83% of the full prompt tuning performance for 100 seen tasks (using different training data) and 20 unseen tasks, respectively, showing great generalization ability of the found intrinsic task subspace. Besides being an analysis tool, IPT could further help us improve the prompt tuning stability.
Code (1)
Similar Papers 제목 키워드 기반
Exploring Low-dimensional Intrinsic Task Subspace via Prompt Tuning
Why can pre-trained language models (PLMs) learn universal representations and effectively adapt to broad NLP tasks differing a lot superficially? In this work, we empirically find evidence indicating that the adaptation…
Fine-tuning Happens in Tiny Subspaces: Exploring Intrinsic Task-specific Subspaces of Pre-trained Language Models
Pre-trained language models (PLMs) are known to be overly parameterized and have significant redundancy, indicating a small degree of freedom of the PLMs. Motivated by the observation, in this paper, we study the problem…
The Universal Weight Subspace Hypothesis
We show that deep neural networks trained across diverse tasks exhibit remarkably similar low-dimensional parametric subspaces. We provide the first large-scale empirical evidence that demonstrates that neural networks s…
Multi-Task LearningExploring Intrinsic Language-specific Subspaces in Fine-tuning Multilingual Neural Machine Translation
Multilingual neural machine translation models support fine-tuning hundreds of languages simultaneously. However, fine-tuning on full parameters solely is inefficient potentially leading to negative interactions among la…
Machine TranslationProRes: Exploring Degradation-aware Visual Prompt for Universal Image Restoration
Image restoration aims to reconstruct degraded images, e.g., denoising or deblurring. Existing works focus on designing task-specific methods and there are inadequate attempts at universal methods. However, simply unifyi…
DeblurringDenoisingImage RestorationLow-Light Image Enhancement+3