Soft Reasoning Paths for Knowledge Graph Completion

• URL: http://arxiv.org/abs/2505.03285v1
• Date: Tue, 06 May 2025 08:12:48 GMT
• Title: Soft Reasoning Paths for Knowledge Graph Completion
• Authors: Yanning Hou, Sihang Zhou, Ke Liang, Lingyuan Meng, Xiaoshu Chen, Ke Xu, Siwei Wang, Xinwang Liu, Jian Huang,
• Abstract summary: Reasoning paths are reliable information in knowledge graph completion (KGC)<n>In real-world applications, it is difficult to guarantee that computationally affordable paths exist toward all candidate entities.<n>We introduce soft reasoning paths to make the proposed algorithm more stable against missing path circumstances.
• Score: 63.23109723605835
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• DataSP: A Differential All-to-All Shortest Path Algorithm for Learning Costs and Predicting Paths with Context [4.202961704179733]
  This paper introduces DataSP, a differentiable all-to-all shortest path algorithm to facilitate learning latent costs from trajectories. Complex latent cost functions from contextual features can be represented in the algorithm through a neural network approximation. We show that DataSP outperforms state-of-the-art machine learning approaches in predicting paths on graphs.
  arXiv  Detail & Related papers  (2024-05-08T09:45:54Z)
• Path Choice Matters for Clear Attribution in Path Methods [84.29092710376217]
  We introduce textbfConcentration Principle, which allocates high attributions to indispensable features. We then present textbfSAMP, a model-agnostic interpreter, which efficiently searches the near-optimal path. We also propose the infinitesimal constraint (IC) and momentum strategy (MS) to improve the rigorousness and optimality.
  arXiv  Detail & Related papers  (2024-01-19T01:11:44Z)
• Discover Important Paths in the Knowledge Graph Based on Dynamic Relation Confidence [2.6032596415721945]
  The reasoning method based on path features is widely used in the field of knowledge graph reasoning. This paper proposes a method called DC-Path that combines dynamic relation confidence and other indicators to evaluate path features.
  arXiv  Detail & Related papers  (2022-11-02T06:37:01Z)
• GraphWalks: Efficient Shape Agnostic Geodesic Shortest Path Estimation [93.60478281489243]
  We propose a learnable network to approximate geodesic paths on 3D surfaces. The proposed method provides efficient approximations of the shortest paths and geodesic distances estimations.
  arXiv  Detail & Related papers  (2022-05-30T16:22:53Z)
• Entity Alignment with Reliable Path Reasoning and Relation-Aware Heterogeneous Graph Transformer [5.960613525368867]
  We propose a more effective entity alignment framework, RPR-RHGT, which integrates relation and path structure information. An initial reliable path reasoning algorithm is developed to generate the paths favorable for EA task from the relation structures of Knowledge Graphs. To efficiently capture heterogeneous features in entity neighborhoods, a relation-aware heterogeneous graph transformer is designed.
  arXiv  Detail & Related papers  (2022-05-18T09:12:37Z)
• PathBench: A Benchmarking Platform for Classical and Learned Path Planning Algorithms [59.3879573040863]
  Path planning is a key component in mobile robotics. Few attempts have been made to benchmark the algorithms holistically or unify their interface. This paper presents PathBench, a platform for developing, visualizing, training, testing, and benchmarking of existing and future path planning algorithms.
  arXiv  Detail & Related papers  (2021-05-04T21:48:18Z)
• Fact Checking via Path Embedding and Aggregation [0.0]
  This paper presents the Fact Checking via path Embedding and Aggregation (FEA) system. FEA starts by carefully collecting the paths between s and o that are most semantically related to the domain of p. We conducted a large set of experiments on a variety of KGs and found that our hybrid solution brings some benefits in terms of performance.
  arXiv  Detail & Related papers  (2020-11-16T15:27:38Z)
• Joint Semantics and Data-Driven Path Representation for Knowledge Graph Inference [60.048447849653876]
  We propose a novel joint semantics and data-driven path representation that balances explainability and generalization in the framework of KG embedding. Our proposed model is evaluated on two classes of tasks: link prediction and path query answering task.
  arXiv  Detail & Related papers  (2020-10-06T10:24:45Z)
• Relational Message Passing for Knowledge Graph Completion [78.47976646383222]
  We propose a relational message passing method for knowledge graph completion. It passes relational messages among edges iteratively to aggregate neighborhood information. Results show our method outperforms stateof-the-art knowledge completion methods by a large margin.
  arXiv  Detail & Related papers  (2020-02-17T03:33:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.