Learning Complete Topology-Aware Correlations Between Relations for Inductive Link Prediction

TL;DR

This paper introduces TACO, a novel method for inductive link prediction that models semantic relation correlations based on topological patterns within subgraphs, improving reasoning over evolving knowledge graphs.

Contribution

The paper proposes a new subgraph-based approach, TACO, which categorizes relation correlations into topological patterns and learns their importance for better inductive link prediction.

Findings

TACO outperforms state-of-the-art methods on inductive link prediction tasks.

The method effectively captures topological and semantic relation correlations.

Complete subgraph patterns enhance the reasoning capability of the model.

Abstract

Inductive link prediction -- where entities during training and inference stages can be different -- has shown great potential for completing evolving knowledge graphs in an entity-independent manner. Many popular methods mainly focus on modeling graph-level features, while the edge-level interactions -- especially the semantic correlations between relations -- have been less explored. However, we notice a desirable property of semantic correlations between relations is that they are inherently edge-level and entity-independent. This implies the great potential of the semantic correlations for the entity-independent inductive link prediction task. Inspired by this observation, we propose a novel subgraph-based method, namely TACO, to model Topology-Aware COrrelations between relations that are highly correlated to their topological structures within subgraphs. Specifically, we prove that semantic correlations between any two relations can be categorized into seven topological patterns, and then proposes Relational Correlation Network (RCN) to learn the importance of each pattern. To further exploit the potential of RCN, we propose Complete Common Neighbor induced subgraph that can effectively preserve complete topological patterns within the subgraph. Extensive experiments demonstrate that TACO effectively unifies the graph-level information and edge-level interactions to jointly perform reasoning, leading to a superior performance over existing state-of-the-art methods for the inductive link prediction task.