Learning transferable representation of knowledge graphs (KGs) is challenging due to the heterogeneous, multi-relational nature of graph structures. Inspired by Transformer-based pretrained language models' success on learning transferable representation for texts, we introduce a novel inductive KG representation model (iHT) for KG completion by large-scale pre-training. iHT consists of a entity encoder (e.g., BERT) and a neighbor-aware relational scoring function both parameterized by Transformers. We first pre-train iHT on a large KG dataset, Wikidata5M. Our approach achieves new state-of-the-art results on matched evaluations, with a relative improvement of more than 25% in mean reciprocal rank over previous SOTA models. When further fine-tuned on smaller KGs with either entity and relational shifts, pre-trained iHT representations are shown to be transferable, significantly improving the performance on FB15K-237 and WN18RR.
@article{arxiv.2303.15682,
title = {Pre-training Transformers for Knowledge Graph Completion},
author = {Sanxing Chen and Hao Cheng and Xiaodong Liu and Jian Jiao and Yangfeng Ji and Jianfeng Gao},
journal= {arXiv preprint arXiv:2303.15682},
year = {2023}
}