Year: 2022
Type: preprint
Abstract: Recent years have witnessed the prevalent application of pre-trained language models (PLMs) in NLP. From the perspective of parameter space, PLMs provide generic initialization, starting from which high-performance minima could be found. Although plenty of works have studied how to effectively and efficiently adapt PLMs to high-performance minima, little is known about the connection of various minima reached under different adaptation configurations. In this paper, we investigate the geometric connections of different minima through the lens of mode connectivity, which measures whether two minima can be connected with a low-loss path. We conduct empirical analyses to investigate three questions: (1) how could hyperparameters, specific tuning methods, and training data affect PLM's mode connectivity? (2) How does mode connectivity change during pre-training? (3) How does the PLM's task knowledge change along the path connecting two minima? In general, exploring the mode connectivity of PLMs conduces to understanding the geometric connection of different minima, which may help us fathom the inner workings of PLM downstream adaptation.
Source: arXiv (Cornell University)
Authors: Qin, Yujia, Qian, Cheng, Yi, Jing, Chen, Weize, Lin, Yankai, Han, Xu, Liu, Zhiyuan, Sun, Maosong, Zhou, Jie
Institutions: Tsinghua University, Renmin University of China, Tencent (China)
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: Tsinghua University
OpenAlex ID: W4307411992