From One Point to A Manifold: Knowledge Graph Embedding For Precise Link Prediction
This addresses the need for more accurate knowledge graph completion in AI applications, representing an incremental advancement over existing methods.
The paper tackles the problem of imprecise link prediction in knowledge graph embedding by proposing ManifoldE, which expands golden triples from points to manifolds, achieving substantial improvements over state-of-the-art baselines while maintaining high efficiency.
Knowledge graph embedding aims at offering a numerical knowledge representation paradigm by transforming the entities and relations into continuous vector space. However, existing methods could not characterize the knowledge graph in a fine degree to make a precise prediction. There are two reasons: being an ill-posed algebraic system and applying an overstrict geometric form. As precise prediction is critical, we propose an manifold-based embedding principle (\textbf{ManifoldE}) which could be treated as a well-posed algebraic system that expands the position of golden triples from one point in current models to a manifold in ours. Extensive experiments show that the proposed models achieve substantial improvements against the state-of-the-art baselines especially for the precise prediction task, and yet maintain high efficiency.