Learning Entity and Relation Embeddings is to represent the entities and relations between them in knowledge graph. Recently a variety of models, starting from the work of TransE, to a series of following work, such as TransH, TransR, TransD, are proposed. These models take a relation as transition from head entity to tail entity in principle. The further researches noticed that relations and entities might be able to have different representation to be cast into real world relations. Thus it improved the embedding accuracy of embeddings. Based on these works, we further noticed that in some real world cases entities representation could be vary, especially when one entity in different positions of a relation. In this paper we proposed a new relation embedding by distinguishing head entity and tail entity. It is possible that an entity can have different semantic meanings in head and tail positions. Motivated by this fact, we defined two different entity spaces, head entities and tail entities, for each type of entities. With the training of the general embeddings learning model, we projected the two entity spaces into relation space to run the stochastic gradient descent (SGD) optimization. Experimental results show our method can have good performance in typical knowledge graphs tasks, such as link prediction.
[1]
Wu-Jun Li,et al.
Lock-Free Optimization for Non-Convex Problems
,
2017,
AAAI.
[2]
Wu-Jun Li,et al.
ParaGraphE: A Library for Parallel Knowledge Graph Embedding
,
2017,
ArXiv.
[3]
Zhen Wang,et al.
Knowledge Graph Embedding by Translating on Hyperplanes
,
2014,
AAAI.
[4]
Han Xiao,et al.
From One Point to a Manifold: Knowledge Graph Embedding for Precise Link Prediction
,
2015,
IJCAI.
[5]
Jun Zhao,et al.
Knowledge Graph Embedding via Dynamic Mapping Matrix
,
2015,
ACL.
[6]
Nicolas Le Roux,et al.
A latent factor model for highly multi-relational data
,
2012,
NIPS.
[7]
George A. Miller,et al.
WordNet: A Lexical Database for English
,
1995,
HLT.
[8]
Jason Weston,et al.
Translating Embeddings for Modeling Multi-relational Data
,
2013,
NIPS.
[9]
Zhiyuan Liu,et al.
Learning Entity and Relation Embeddings for Knowledge Graph Completion
,
2015,
AAAI.
[10]
Stephen J. Wright,et al.
Hogwild: A Lock-Free Approach to Parallelizing Stochastic Gradient Descent
,
2011,
NIPS.
[11]
Praveen Paritosh,et al.
Freebase: a collaboratively created graph database for structuring human knowledge
,
2008,
SIGMOD Conference.