Information Guided Regularization for Fine-tuning Language Models
Abstract
The pretraining-fine-tuning paradigm has been the de facto strategy for transfer learning in modern language modeling. With the understanding that task adaptation in LMs is often a function of parameters shared across tasks, we argue that a more surgical approach to regularization needs to exist for smoother transfer learning. Towards this end, we investigate how the pretraining loss landscape is affected by these task-sensitive parameters through an information-theoretic lens. We then leverage the findings from our investigations to devise a novel approach to dropout for improved model regularization and better downstream generalization. This approach, named guided dropout, is both task & architecture agnostic and adds no computational overhead to the fine-tuning process. Through empirical evaluations, we showcase that our approach to regularization yields consistently better performance, even in scenarios of data paucity, compared to standardized baselines.
Cite
@article{arxiv.2406.14005,
title = {Information Guided Regularization for Fine-tuning Language Models},
author = {Mandar Sharma and Nikhil Muralidhar and Shengzhe Xu and Raquib Bin Yousuf and Naren Ramakrishnan},
journal= {arXiv preprint arXiv:2406.14005},
year = {2024}
}