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

TL;DR

This paper introduces a novel graph-based method for link prediction in n-ary relational facts within knowledge graphs, effectively modeling complex relationships with a heterogeneous graph and attention mechanisms.

Contribution

It proposes a new approach that models n-ary relations as heterogeneous graphs using edge-biased attention, improving link prediction accuracy over existing methods.

Findings

Outperforms state-of-the-art methods on multiple n-ary relational benchmarks.

Effectively captures global and local dependencies in n-ary facts.

Demonstrates robustness and generalizability across diverse datasets.

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.