A Structural Representation Learning for Multi-relational Networks

Abstract

Most of the existing multi-relational network embedding methods, e.g., TransE, are formulated to preserve pair-wise connectivity structures in the networks. With the observations that significant triangular connectivity structures and parallelogram connectivity structures found in many real multi-relational networks are often ignored and that a hard-constraint commonly adopted by most of the network embedding methods is inaccurate by design, we propose a novel representation learning model for multi-relational networks which can alleviate both fundamental limitations. Scalable learning algorithms are derived using the stochastic gradient descent algorithm and negative sampling. Extensive experiments on real multi-relational network datasets of WordNet and Freebase demonstrate the efficacy of the proposed model when compared with the state-of-the-art embedding methods.

References in corpus (7)

• Distributed Representations of Words and Phrases and their Compositionality
• word2vec Explained: deriving Mikolov et al.'s negative-sampling word-embedding method
• GraphGAN: Graph Representation Learning with Generative Adversarial Nets
• Modeling Relation Paths for Representation Learning of Knowledge Bases
• TransG : A Generative Mixture Model for Knowledge Graph Embedding
• Adversarial Network Embedding
• TorusE: Knowledge Graph Embedding on a Lie Group

Cited by in corpus (2)

• mvn2vec: Preservation and Collaboration in Multi-View Network Embedding
• A Survey of Embedding Space Alignment Methods for Language and Knowledge Graphs