MetaFill: Text Infilling for Meta-Path Generation on Heterogeneous Information Networks

Zequn Liu, Kefei Duan, Junwei Yang, Hanwen Xu, Ming Zhang, Sheng Wang


Abstract
Heterogeneous information network (HIN) is essential to study complicated networks containing multiple edge types and node types. Meta-path, a sequence of node types and edge types, is the core technique to embed HINs. Since manually curating meta-paths is time-consuming, there is a pressing need to develop automated meta-path generation approaches. Existing meta-path generation approaches cannot fully exploit the rich textual information in HINs, such as node names and edge type names. To address this problem, we propose MetaFill, a text-infilling-based approach for meta-path generation. The key idea of MetaFill is to formulate meta-path identification problem as a word sequence infilling problem, which can be advanced by pretrained language models (PLMs). We observed the superior performance of MetaFill against existing meta-path generation methods and graph embedding methods that do not leverage meta-paths in both link prediction and node classification on two real-world HIN datasets. We further demonstrated how MetaFill can accurately classify edges in the zero-shot setting, where existing approaches cannot generate any meta-paths. MetaFill exploits PLMs to generate meta-paths for graph embedding, opening up new avenues for language model applications in graph analysis.
Anthology ID:
2022.emnlp-main.341
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5110–5122
Language:
URL:
https://aclanthology.org/2022.emnlp-main.341
DOI:
10.18653/v1/2022.emnlp-main.341
Bibkey:
Cite (ACL):
Zequn Liu, Kefei Duan, Junwei Yang, Hanwen Xu, Ming Zhang, and Sheng Wang. 2022. MetaFill: Text Infilling for Meta-Path Generation on Heterogeneous Information Networks. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 5110–5122, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
MetaFill: Text Infilling for Meta-Path Generation on Heterogeneous Information Networks (Liu et al., EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-main.341.pdf