A Comparative Study of Pre-training and Self-training

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Yiheng, Lin, Jiayu, Lin, Zuoquan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912014611251200
author Wang, Yiheng
Lin, Jiayu
Lin, Zuoquan
author_facet Wang, Yiheng
Lin, Jiayu
Lin, Zuoquan
contents Pre-training and self-training are two approaches to semi-supervised learning. The comparison between pre-training and self-training has been explored. However, the previous works led to confusing findings: self-training outperforms pre-training experienced on some tasks in computer vision, and contrarily, pre-training outperforms self-training experienced on some tasks in natural language processing, under certain conditions of incomparable settings. We propose, comparatively and exhaustively, an ensemble method to empirical study all feasible training paradigms combining pre-training, self-training, and fine-tuning within consistent foundational settings comparable to data augmentation. We conduct experiments on six datasets, four data augmentation, and imbalanced data for sentiment analysis and natural language inference tasks. Our findings confirm that the pre-training and fine-tuning paradigm yields the best overall performances. Moreover, self-training offers no additional benefits when combined with semi-supervised pre-training.
format Preprint
id arxiv_https___arxiv_org_abs_2409_02751
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Comparative Study of Pre-training and Self-training
Wang, Yiheng
Lin, Jiayu
Lin, Zuoquan
Computation and Language
Pre-training and self-training are two approaches to semi-supervised learning. The comparison between pre-training and self-training has been explored. However, the previous works led to confusing findings: self-training outperforms pre-training experienced on some tasks in computer vision, and contrarily, pre-training outperforms self-training experienced on some tasks in natural language processing, under certain conditions of incomparable settings. We propose, comparatively and exhaustively, an ensemble method to empirical study all feasible training paradigms combining pre-training, self-training, and fine-tuning within consistent foundational settings comparable to data augmentation. We conduct experiments on six datasets, four data augmentation, and imbalanced data for sentiment analysis and natural language inference tasks. Our findings confirm that the pre-training and fine-tuning paradigm yields the best overall performances. Moreover, self-training offers no additional benefits when combined with semi-supervised pre-training.
title A Comparative Study of Pre-training and Self-training
topic Computation and Language
url https://arxiv.org/abs/2409.02751