How Does Knowledge Graph Embedding Extrapolate to Unseen Data: A Semantic Evidence View

作者：Ren Li, Yanan Cao, Qiannan Zhu, Guanqun Bi, Fang Fang, Yi Liu, Qian Li · 发表于：Proceedings of the AAAI Conference on Artificial Intelligence · 年份：2022 · DOI：10.1609/aaai.v36i5.20521 · 被引用次数：80 · 研究领域：Advanced Graph Neural Networks、Topic Modeling、Domain Adaptation and Few-Shot Learning

Knowledge Graph Embedding (KGE) aims to learn representations for entities and relations. Most KGE models have gained great success, especially on extrapolation scenarios. Specifically, given an unseen triple (h, r, t), a trained model can still correctly predict t from (h, r, ?), or h from (?, r, t), such extrapolation ability is impressive. However, most existing KGE works focus on the design of delicate triple modeling function, which mainly tells us how to measure the plausibility of observed triples, but offers limited explanation of why the methods can extrapolate to unseen data, and what are the important factors to help KGE extrapolate. Therefore in this work, we attempt to study the KGE extrapolation of two problems: 1. How does KGE extrapolate to unseen data? 2. How to design the KGE model with better extrapolation ability? For the problem 1, we first discuss the impact factors for extrapolation and from relation, entity and triple level respectively, propose three Semantic Evidences (SEs), which can be observed from train set and provide important semantic information for extrapolation. Then we verify the effectiveness of SEs through extensive experiments on several typical KGE methods. For the problem 2, to make better use of the three levels of SE, we propose a novel GNN-based KGE model, called Semantic Evidence aware Graph Neural Network (SE-GNN). In SE-GNN, each level of SE is modeled explicitly by the corresponding neighbor pattern, and merged sufficiently by ...