From One Point to A Manifold: Orbit Models for Knowledge Graph Embedding.
Han Xiao, Minlie Huang, Yu Hao, Xiaoyan Zhu · arXiv (Cornell University) · 2015
Knowledge graph embedding aims at offering a numerical paradigm for knowledge representation by translating the entities and relations into continuous vector space. This paper studies the problem of unsatisfactory precise knowledge embedding and attributes a new issue to this problem that \textbf{\textit{inaccuracy of truth characterization}}, indicating that existing methods could not express the true facts in a fine degree. To alleviate this issue, we propose the orbit-based embedding model, \textbf{OrbitE}. The new model is a well-posed algebraic system that expands the position of golden triples from one point in current models to a manifold. Extensive experiments show that the proposed model achieves substantial improvements against the state-of-the-art baselines, especially for precise prediction.