Trans4E: Link Prediction on Scholarly Knowledge Graphs

TL;DR

Trans4E is a new embedding model designed for link prediction in scholarly knowledge graphs, especially effective for large N to M relations, improving data completeness and accuracy in research-related KGs.

Contribution

We introduce Trans4E, a novel embedding model optimized for N to M relations in large-scale scholarly knowledge graphs, demonstrating superior performance in link prediction tasks.

Findings

Trans4E outperforms existing models at low embedding dimensions.

Trans4E achieves competitive results at high embedding dimensions.

Applied to large-scale KGs, Trans4E improves data completeness and accuracy.

Abstract

The incompleteness of Knowledge Graphs (KGs) is a crucial issue affecting the quality of AI-based services. In the scholarly domain, KGs describing research publications typically lack important information, hindering our ability to analyse and predict research dynamics. In recent years, link prediction approaches based on Knowledge Graph Embedding models became the first aid for this issue. In this work, we present Trans4E, a novel embedding model that is particularly fit for KGs which include N to M relations with N$\gg$M. This is typical for KGs that categorize a large number of entities (e.g., research articles, patents, persons) according to a relatively small set of categories. Trans4E was applied on two large-scale knowledge graphs, the Academia/Industry DynAmics (AIDA) and Microsoft Academic Graph (MAG), for completing the information about Fields of Study (e.g., 'neural networks', 'machine learning', 'artificial intelligence'), and affiliation types (e.g., 'education', 'company', 'government'), improving the scope and accuracy of the resulting data. We evaluated our approach against alternative solutions on AIDA, MAG, and four other benchmarks (FB15k, FB15k-237, WN18, and WN18RR). Trans4E outperforms the other models when using low embedding dimensions and obtains competitive results in high dimensions.