Knowledge Graph Embedding by Translating on Hyperplanes
نویسندگان
چکیده
We deal with embedding a large scale knowledge graph composed of entities and relations into a continuous vector space. TransE is a promising method proposed recently, which is very efficient while achieving state-of-the-art predictive performance. We discuss some mapping properties of relations which should be considered in embedding, such as reflexive, one-to-many, many-to-one, and many-to-many. We note that TransE does not do well in dealing with these properties. Some complex models are capable of preserving these mapping properties but sacrifice efficiency in the process. To make a good trade-off between model capacity and efficiency, in this paper we propose TransH which models a relation as a hyperplane together with a translation operation on it. In this way, we can well preserve the above mapping properties of relations with almost the same model complexity of TransE. Additionally, as a practical knowledge graph is often far from completed, how to construct negative examples to reduce false negative labels in training is very important. Utilizing the one-to-many/many-to-one mapping property of a relation, we propose a simple trick to reduce the possibility of false negative labeling. We conduct extensive experiments on link prediction, triplet classification and fact extraction on benchmark datasets like WordNet and Freebase. Experiments show TransH delivers significant improvements over TransE on predictive accuracy with comparable capability to scale up.
منابع مشابه
ParaGraphE: A Library for Parallel Knowledge Graph Embedding
Knowledge graph embedding aims at translating the knowledge graph into numerical representations by transforming the entities and relations into continuous low-dimensional vectors. Recently, many methods [1, 5, 3, 2, 6] have been proposed to deal with this problem, but existing single-thread implementations of them are time-consuming for large-scale knowledge graphs. Here, we design a unified p...
متن کاملPoints and hyperplanes of the universal embedding space of the dual polar space DW ( 5 , q ) , q odd
In [10], one of the authors proved that there are 6 isomorphism classes of hyperplanes in the dual polar space DW (5, q), q even, which arise from its Grassmann-embedding. In the present paper, we extend these results to the case that q is odd. Specifically, we determine the orbits of the full automorphism group of DW (5, q), q odd, on the projective points (or equivalently, the hyperplanes) of...
متن کاملDetecting Overlapping Communities in Social Networks using Deep Learning
In network analysis, a community is typically considered of as a group of nodes with a great density of edges among themselves and a low density of edges relative to other network parts. Detecting a community structure is important in any network analysis task, especially for revealing patterns between specified nodes. There is a variety of approaches presented in the literature for overlapping...
متن کاملThe hyperplanes of DW(5, 2h) which arise from embedding
We show that there are 6 isomorphism classes of hyperplanes of the dual polar space ∆ = DW (5, 2h) which arise from the Grassmannembedding. If h ≥ 2, then these are all the hyperplanes of ∆ arising from an embedding. If h = 1, then there are 6 extra classes of hyperplanes as has been shown by Pralle [23] with the aid of a computer. We will give a computer free proof for this fact. The hyperplan...
متن کامل