Deep Sparse Latent Feature Models for Knowledge Graph Completion
This work addresses the problem of missing triple completion in knowledge graphs for applications requiring structured data, representing an incremental improvement by hybridizing existing methods.
The paper tackles knowledge graph completion by developing a probabilistic framework that combines sparse latent feature models with a deep variational autoencoder to integrate global clustering information with local textual features, achieving significant performance gains on four benchmark datasets.
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.