Enhancing Knowledge Graph Embedding with Probabilistic Negative Sampling
Vibhor Kanojia, Hideyuki Maeda, Riku Togashi, Sumio Fujita
WWW 2017 (26th International Conference on World Wide Web) Posters, 2017/4
情報検索 (Information Retrieval) 機械学習 (Machine Learning) セマンティック・ウェブ (Semantic Web)
- Link Prediction using Knowledge graph embedding projects symbolic entities and relations into low dimensional vector space, thereby learning the semantic relations between entities. Among various embedding models, there is a series of translation-based models such as TransE, TransH, and TransR. This paper proposes modifications in the TransR model to address the issue of skewed data which is common in real-world knowledge graphs. The enhancements enable the model to smartly generate corrupted triplets during negative sampling, which significantly improves the training time and performance of TransR. The proposed approach can be applied to other translation based models.
Enhancing Knowledge Graph Embedding with Probabilistic Negative Sampling（外部サイト／External Site Link）