StruProKGR: A Structural and Probabilistic Framework for Sparse Knowledge Graph Reasoning
This work addresses sparse knowledge graph reasoning, a domain-specific challenge in AI for applications with incomplete data, offering incremental improvements in efficiency and effectiveness over prior path-based approaches.
The paper tackles the problem of inferring missing knowledge in sparse knowledge graphs by proposing StruProKGR, a framework that improves efficiency and interpretability through distance-guided path collection and probabilistic aggregation, achieving superior performance on five benchmarks compared to existing methods.
Sparse Knowledge Graphs (KGs) are commonly encountered in real-world applications, where knowledge is often incomplete or limited. Sparse KG reasoning, the task of inferring missing knowledge over sparse KGs, is inherently challenging due to the scarcity of knowledge and the difficulty of capturing relational patterns in sparse scenarios. Among all sparse KG reasoning methods, path-based ones have attracted plenty of attention due to their interpretability. Existing path-based methods typically rely on computationally intensive random walks to collect paths, producing paths of variable quality. Additionally, these methods fail to leverage the structured nature of graphs by treating paths independently. To address these shortcomings, we propose a Structural and Probabilistic framework named StruProKGR, tailored for efficient and interpretable reasoning on sparse KGs. StruProKGR utilizes a distance-guided path collection mechanism to significantly reduce computational costs while exploring more relevant paths. It further enhances the reasoning process by incorporating structural information through probabilistic path aggregation, which prioritizes paths that reinforce each other. Extensive experiments on five sparse KG reasoning benchmarks reveal that StruProKGR surpasses existing path-based methods in both effectiveness and efficiency, providing an effective, efficient, and interpretable solution for sparse KG reasoning.