Transductive Data Augmentation with Relational Path Rule Mining for Knowledge Graph Embedding

TL;DR

This paper introduces a transductive data augmentation method using relation path rules with confidence weighting to enhance knowledge graph embedding models, achieving improved prediction accuracy by effectively utilizing low-confidence rules.

Contribution

It proposes a novel transductive data augmentation approach that leverages relation path rules with confidence scores, improving knowledge graph embedding performance.

Findings

Enhanced embedding accuracy through augmented data.

Effective utilization of low-confidence relation rules.

Improved knowledge graph completion results.

Abstract

For knowledge graph completion, two major types of prediction models exist: one based on graph embeddings, and the other based on relation path rule induction. They have different advantages and disadvantages. To take advantage of both types, hybrid models have been proposed recently. One of the hybrid models, UniKER, alternately augments training data by relation path rules and trains an embedding model. Despite its high prediction accuracy, it does not take full advantage of relation path rules, as it disregards low-confidence rules in order to maintain the quality of augmented data. To mitigate this limitation, we propose transductive data augmentation by relation path rules and confidence-based weighting of augmented data. The results and analysis show that our proposed method effectively improves the performance of the embedding model by augmenting data that include true answers or entities similar to them.