Clarified Aggregation and Predictive Modeling (CAPM): High-Interpretability Framework for Inductive Link Prediction

• Main Authors: Xiao, Mengxi, Liu, Ben, Peng, Miao, Xu, Wenjie, Peng, Min
• Format: Conference Proceeding
• Language: English
• Subjects: Attention mechanisms; inductive link prediction; knowledge graph completion; Knowledge graphs; Limiting; message aggregation; model interpretability; Neural networks; Predictive models; Semantics
• ISSN: 2161-4407
• DOI: 10.1109/IJCNN60899.2024.10650892

In inductive link prediction for evolving knowledge graphs (KGs), interpretability is crucial yet often overlooked in relational message aggregation methods. Previous approaches typically neglect deeper relational insights, limiting their explanatory power. In this paper, we propose CAPM (Constrained Aggregation and Predictive Modeling) to address this critical gap by uniquely incorporating semantic descriptions of entities. This integration allows for a clearer understanding of how and why certain links are predicted and strengthens its ability to contextualize and clarify the relationships within the KG. In particular, CAPM combines entity type and an attention mechanism during aggregation, ensuring a sophisticated blend of structured and semantic information. This method also improves relevance assessment in relational paths, leveraging prior knowledge in adjacent relations. Tested on sparse KGs, CAPM demonstrates exceptional performance in inductive link prediction scenarios. Ablation studies confirm its superiority, particularly when combined with embedding-based methods for entity-type representation, highlighting its effectiveness in evolving KGs. Through this innovative approach, CAPM offers a comprehensive solution that balances the dynamic nature of KGs with the essential need for interpretability in link prediction.