Fine-tuning Happens in Tiny Subspaces: Exploring Intrinsic Task-specific Subspaces of Pre-trained Language Models
Zhang, Zhong, Liu, Bang, Shao, Junming
–arXiv.org Artificial Intelligence
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 of re-parameterizing and fine-tuning PLMs from a new perspective: Discovery of intrinsic task-specific subspace. Specifically, by exploiting the dynamics of the fine-tuning process for a given task, the parameter optimization trajectory is learned to uncover its intrinsic task-specific subspace. A key finding is that PLMs can be effectively fine-tuned in the subspace with a small number of free parameters. Beyond, we observe some outlier dimensions emerging during fine-tuning in the subspace. Disabling these dimensions degrades the model performance significantly. This suggests that these dimensions are crucial to induce task-specific knowledge to downstream tasks.
arXiv.org Artificial Intelligence
Aug-1-2023
- Country:
- North America > Canada
- Asia > China
- Guangdong Province > Shenzhen (0.04)
- Sichuan Province > Chengdu (0.04)
- Genre:
- Research Report (1.00)
- Technology: