Bayes EMbedding (BEM): Refining Representation by Integrating Knowledge Graphs and Behavior-specific Networks

TL;DR

BEM is a Bayesian framework that enhances entity embeddings by integrating knowledge graph and behavior graph information, leading to improved performance in various graph-related tasks.

Contribution

It introduces a unified Bayesian model that refines embeddings by combining pre-trained knowledge and behavior graph representations, a novel approach in this domain.

Findings

Outperforms existing methods in node classification and link prediction

Effectively refines embeddings while preserving topological structures

Demonstrates superior results on multiple benchmark datasets

Abstract

Low-dimensional embeddings of knowledge graphs and behavior graphs have proved remarkably powerful in varieties of tasks, from predicting unobserved edges between entities to content recommendation. The two types of graphs can contain distinct and complementary information for the same entities/nodes. However, previous works focus either on knowledge graph embedding or behavior graph embedding while few works consider both in a unified way. Here we present BEM , a Bayesian framework that incorporates the information from knowledge graphs and behavior graphs. To be more specific, BEM takes as prior the pre-trained embeddings from the knowledge graph, and integrates them with the pre-trained embeddings from the behavior graphs via a Bayesian generative model. BEM is able to mutually refine the embeddings from both sides while preserving their own topological structures. To show the superiority of our method, we conduct a range of experiments on three benchmark datasets: node classification, link prediction, triplet classification on two small datasets related to Freebase, and item recommendation on a large-scale e-commerce dataset.