English

Link Prediction on N-ary Relational Facts: A Graph-based Approach

Artificial Intelligence 2021-05-19 v1

Abstract

Link prediction on knowledge graphs (KGs) is a key research topic. Previous work mainly focused on binary relations, paying less attention to higher-arity relations although they are ubiquitous in real-world KGs. This paper considers link prediction upon n-ary relational facts and proposes a graph-based approach to this task. The key to our approach is to represent the n-ary structure of a fact as a small heterogeneous graph, and model this graph with edge-biased fully-connected attention. The fully-connected attention captures universal inter-vertex interactions, while with edge-aware attentive biases to particularly encode the graph structure and its heterogeneity. In this fashion, our approach fully models global and local dependencies in each n-ary fact, and hence can more effectively capture associations therein. Extensive evaluation verifies the effectiveness and superiority of our approach. It performs substantially and consistently better than current state-of-the-art across a variety of n-ary relational benchmarks. Our code is publicly available.

Keywords

Cite

@article{arxiv.2105.08476,
  title  = {Link Prediction on N-ary Relational Facts: A Graph-based Approach},
  author = {Quan Wang and Haifeng Wang and Yajuan Lyu and Yong Zhu},
  journal= {arXiv preprint arXiv:2105.08476},
  year   = {2021}
}

Comments

Accepted to Findings of ACL 2021

R2 v1 2026-06-24T02:13:19.226Z