MOHONE: Modeling Higher Order Network Effects in KnowledgeGraphs via Network Infused Embeddings

TL;DR

MOHONE introduces a flexible framework for modeling higher order network effects in knowledge graphs, improving link prediction by integrating local and global network similarities into embeddings.

Contribution

It presents a generic method to explicitly model network scale and similarity types, enhancing existing knowledge graph embeddings with higher order network information.

Findings

Significantly improves link prediction accuracy (up to 17%).

Effectively captures local neighborhood and structural role similarities.

Enhances multiple embedding methods like TRANSE, DISTMULT, and COMPLEX.

Abstract

Many knowledge graph embedding methods operate on triples and are therefore implicitly limited by a very local view of the entire knowledge graph. We present a new framework MOHONE to effectively model higher order network effects in knowledge-graphs, thus enabling one to capture varying degrees of network connectivity (from the local to the global). Our framework is generic, explicitly models the network scale, and captures two different aspects of similarity in networks: (a) shared local neighborhood and (b) structural role-based similarity. First, we introduce methods that learn network representations of entities in the knowledge graph capturing these varied aspects of similarity. We then propose a fast, efficient method to incorporate the information captured by these network representations into existing knowledge graph embeddings. We show that our method consistently and significantly improves the performance on link prediction of several different knowledge-graph embedding methods including TRANSE, TRANSD, DISTMULT, and COMPLEX(by at least 4 points or 17% in some cases).