Soft Reasoning Paths for Knowledge Graph Completion

2025-05-06

AI Summary

To address the sharp performance degradation and poor robustness in knowledge graph completion (KGC) caused by missing inference paths, this paper proposes a soft reasoning path mechanism. It introduces learnable latent path embeddings jointly modeled with relations to generalize representation for incomplete or unreachable paths. A relation–soft-path coupling encoding module and a hierarchical multi-granularity scoring and ranking strategy are designed to synergistically integrate entity, relation, explicit path, and soft path information. Crucially, this work is the first to formulate “soft paths” as continuous, differentiable implicit structures amenable to end-to-end optimization. Evaluated on standard benchmarks—including FB15k-237 and WN18RR—the method achieves significant improvements over state-of-the-art approaches, yielding up to a 3.2% gain in accuracy under sparse-path conditions and markedly enhanced model stability.

Technology Category

• Knowledge Representation and Reasoning: Computational Complexity of Reasoning
• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Reasoning paths are reliable information in knowledge graph completion (KGC) in which algorithms can find strong clues of the actual relation between entities. However, in real-world applications, it is difficult to guarantee that computationally affordable paths exist toward all candidate entities. According to our observation, the prediction accuracy drops significantly when paths are absent. To make the proposed algorithm more stable against the missing path circumstances, we introduce soft reasoning paths. Concretely, a specific learnable latent path embedding is concatenated to each relation to help better model the characteristics of the corresponding paths. The combination of the relation and the corresponding learnable embedding is termed a soft path in our paper. By aligning the soft paths with the reasoning paths, a learnable embedding is guided to learn a generalized path representation of the corresponding relation. In addition, we introduce a hierarchical ranking strategy to make full use of information about the entity, relation, path, and soft path to help improve both the efficiency and accuracy of the model. Extensive experimental results illustrate that our algorithm outperforms the compared state-of-the-art algorithms by a notable margin. The code will be made publicly available after the paper is officially accepted.

Problem

• Addresses missing paths in knowledge graph completion
• Introduces soft reasoning paths for stable predictions
• Proposes hierarchical ranking to enhance model accuracy

Innovation

• Introduces soft reasoning paths for missing data
• Uses learnable latent path embeddings for relations
• Implements hierarchical ranking for efficiency and accuracy