Prior Bilinear Based Models for Knowledge Graph Completion
This work addresses a specific limitation in knowledge graph completion for AI applications, but it is incremental as it builds on existing bilinear models.
The paper tackles the problem that bilinear models for knowledge graph completion neglect prior properties like the 'law of identity', which hinders comprehensive modeling, and introduces the Unit Ball Bilinear Model (UniBi) to address this, achieving theoretical superiority and enhanced interpretability and performance.
Bilinear based models are powerful and widely used approaches for Knowledge Graphs Completion (KGC). Although bilinear based models have achieved significant advances, these studies mainly concentrate on posterior properties (based on evidence, e.g. symmetry pattern) while neglecting the prior properties. In this paper, we find a prior property named "the law of identity" that cannot be captured by bilinear based models, which hinders them from comprehensively modeling the characteristics of KGs. To address this issue, we introduce a solution called Unit Ball Bilinear Model (UniBi). This model not only achieves theoretical superiority but also offers enhanced interpretability and performance by minimizing ineffective learning through minimal constraints. Experiments demonstrate that UniBi models the prior property and verify its interpretability and performance.