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

Autor:	Hirose, Yushi, Shimbo, Masashi, Watanabe, Taro
Rok vydání:	2021
Předmět:	Computer Science - Machine Learning Computer Science - Computation and Language Computer Science - Information Retrieval
Druh dokumentu:	Working Paper
Popis:	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. Comment: 8 pages, 0 figures, accepted by 2021 IEEE International Conference on Big Knowledge. The copyright of this paper has been transferred to the IEEE, please comply with the copyright of the IEEE
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2111.00974 Zobrazit plný text záznamu View this record from Arxiv