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.
Anthology ID:
2022.findings-emnlp.281
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3833–3847
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.281
DOI:
10.18653/v1/2022.findings-emnlp.281
Bibkey:
Cite (ACL):
Jianhao Shen, Chenguang Wang, Ye Yuan, Jiawei Han, Heng Ji, Koushik Sen, Ming Zhang, and Dawn Song. 2022. PALT: Parameter-Lite Transfer of Language Models for Knowledge Graph Completion. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 3833–3847, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
PALT: Parameter-Lite Transfer of Language Models for Knowledge Graph Completion (Shen et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-emnlp.281.pdf
Video:
 https://aclanthology.org/2022.findings-emnlp.281.mp4