Soft Reasoning Paths for Knowledge Graph Completion

TL;DR

This paper introduces soft reasoning paths with learnable embeddings to improve knowledge graph completion, especially in scenarios with missing paths, achieving superior accuracy over state-of-the-art methods.

Contribution

It proposes a novel soft path model with hierarchical ranking to enhance stability and performance in knowledge graph completion tasks.

Findings

Outperforms state-of-the-art algorithms significantly

Improves robustness against missing path scenarios

Enhances efficiency and accuracy through hierarchical ranking

Abstract

Reasoning paths are reliable information in knowledge graph completion (KGC) in which algorithms can find strong clues of the actual relation between entities. However, in real-world applications, it is difficult to guarantee that computationally affordable paths exist toward all candidate entities. According to our observation, the prediction accuracy drops significantly when paths are absent. To make the proposed algorithm more stable against the missing path circumstances, we introduce soft reasoning paths. Concretely, a specific learnable latent path embedding is concatenated to each relation to help better model the characteristics of the corresponding paths. The combination of the relation and the corresponding learnable embedding is termed a soft path in our paper. By aligning the soft paths with the reasoning paths, a learnable embedding is guided to learn a generalized path representation of the corresponding relation. In addition, we introduce a hierarchical ranking strategy to make full use of information about the entity, relation, path, and soft path to help improve both the efficiency and accuracy of the model. Extensive experimental results illustrate that our algorithm outperforms the compared state-of-the-art algorithms by a notable margin. The code will be made publicly available after the paper is officially accepted.