Transductive Data Augmentation with Relational Path Rule Mining for Knowledge Graph Embedding
This work addresses knowledge graph completion for AI applications, but it is incremental as it builds on existing hybrid models like UniKER.
The paper tackled the limitation of hybrid models for knowledge graph completion by proposing transductive data augmentation with confidence-based weighting, which improved embedding model performance by effectively including low-confidence rules and similar entities.
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.