PALT: Parameter-Lite Transfer of Language Models for Knowledge Graph Completion
Jianhao Shen, Chenguang Wang, Ye Yuan, Jiawei Han, Heng Ji, Koushik Sen, Ming Zhang, Dawn Song
Abstract
This paper presents a parameter-lite transfer learning approach of pretrained language models (LM) for knowledge graph (KG) completion. Instead of finetuning, which modifies all LM parameters, we only tune a few new parameters while keeping the original LM parameters fixed. We establish this via reformulating KG completion as a “fill-in-the-blank” task, and introducing a parameter-lite encoder on top of the original LMs. We show that, by tuning far fewer parameters than finetuning, LMs transfer non-trivially to most tasks and reach competitiveness with prior state-of-the-art approaches. For instance, we outperform the fully finetuning approaches on a KG completion benchmark by tuning only 1% of the parameters.
BibTeX
@inproceedings{shen-etal-2022-palt,
title = "{PALT}: Parameter-Lite Transfer of Language Models for Knowledge Graph Completion",
author = "Shen, Jianhao and
Wang, Chenguang and
Yuan, Ye and
Han, Jiawei and
Ji, Heng and
Sen, Koushik and
Zhang, Ming and
Song, Dawn",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.281/",
doi = "10.18653/v1/2022.findings-emnlp.281",
pages = "3833--3847"
}