Deep Sparse Latent Feature Models for Knowledge Graph Completion

TL;DR

This paper introduces a deep variational autoencoder-based sparse latent feature model for knowledge graph completion, effectively combining global structural information with local textual features to improve link prediction and interpretability.

Contribution

It presents a novel probabilistic framework that integrates global clustering with local textual features using a deep VAE, advancing knowledge graph completion methods.

Findings

Significant performance improvements on benchmark datasets

Enhanced interpretability of latent structures

Effective integration of global and local features

Abstract

Recent advances in knowledge graph completion (KGC) have emphasized text-based approaches to navigate the inherent complexities of large-scale knowledge graphs (KGs). While these methods have achieved notable progress, they frequently struggle to fully incorporate the global structural properties of the graph. Stochastic blockmodels (SBMs), especially the latent feature relational model (LFRM), offer robust probabilistic frameworks for identifying latent community structures and improving link prediction. This paper presents a novel probabilistic KGC framework utilizing sparse latent feature models, optimized via a deep variational autoencoder (VAE). Our proposed method dynamically integrates global clustering information with local textual features to effectively complete missing triples, while also providing enhanced interpretability of the underlying latent structures. Extensive experiments on four benchmark datasets with varying scales demonstrate the significant performance gains achieved by our method.