MetaFill: Text Infilling for Meta-Path Generation on Heterogeneous Information Networks
This addresses the time-consuming manual curation of meta-paths for researchers and practitioners in graph analysis, offering a novel method that leverages textual information.
The paper tackles the problem of automated meta-path generation in Heterogeneous Information Networks (HINs) by proposing MetaFill, a text-infilling-based approach that uses Pretrained Language Models (PLMs), achieving superior performance in link prediction and node classification on two real-world datasets and enabling zero-shot edge classification.
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.