CLFeb 10, 2022

InterHT: Knowledge Graph Embeddings by Interaction between Head and Tail Entities

arXiv:2202.04897v213 citations
AI Analysis

This work addresses a bottleneck in knowledge graph completion for AI applications, though it appears incremental as it builds on existing distance-based methods.

The authors tackled the problem of limited model capacity in distance-based knowledge graph embedding methods by proposing InterHT and InterHT+, which enable better interaction between head and tail entities, achieving state-of-the-art results on the ogbl-wikikg2 dataset.

Knowledge graph embedding (KGE) models learn the representation of entities and relations in knowledge graphs. Distance-based methods show promising performance on link prediction task, which predicts the result by the distance between two entity representations. However, most of these methods represent the head entity and tail entity separately, which limits the model capacity. We propose two novel distance-based methods named InterHT and InterHT+ that allow the head and tail entities to interact better and get better entity representation. Experimental results show that our proposed method achieves the best results on ogbl-wikikg2 dataset.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes