SLogic: Subgraph-Informed Logical Rule Learning for Knowledge Graph Completion
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911371011031040 |
|---|---|
| author | Le, Trung Hoang Son, Tran Cao Cao, Huiping |
| author_facet | Le, Trung Hoang Son, Tran Cao Cao, Huiping |
| contents | Logical rule-based methods offer an interpretable approach to knowledge graph completion (KGC) by capturing compositional relationships in the form of human-readable inference rules. While existing logical rule-based methods learn rule confidence scores, they typically assign a global weight to each rule schema, applied uniformly across the graph. This is a significant limitation, as a rule's importance often varies depending on the specific query instance. To address this, we introduce SLogic (Subgraph-Informed Logical Rule learning), a novel framework that assigns query-dependent scores to logical rules. The core of SLogic is a context-aware scoring function. This function determines the importance of a rule by analyzing the subgraph locally defined by the query's head entity, thereby enabling a differentiated weighting of rules specific to their local query contexts. Extensive experiments on benchmark datasets show that SLogic outperforms existing rule-based methods and achieves competitive performance against state-of-the-art baselines. It also generates query-dependent, human-readable logical rules that serve as explicit explanations for its inferences. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_00279 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SLogic: Subgraph-Informed Logical Rule Learning for Knowledge Graph Completion Le, Trung Hoang Son, Tran Cao Cao, Huiping Machine Learning Artificial Intelligence Logical rule-based methods offer an interpretable approach to knowledge graph completion (KGC) by capturing compositional relationships in the form of human-readable inference rules. While existing logical rule-based methods learn rule confidence scores, they typically assign a global weight to each rule schema, applied uniformly across the graph. This is a significant limitation, as a rule's importance often varies depending on the specific query instance. To address this, we introduce SLogic (Subgraph-Informed Logical Rule learning), a novel framework that assigns query-dependent scores to logical rules. The core of SLogic is a context-aware scoring function. This function determines the importance of a rule by analyzing the subgraph locally defined by the query's head entity, thereby enabling a differentiated weighting of rules specific to their local query contexts. Extensive experiments on benchmark datasets show that SLogic outperforms existing rule-based methods and achieves competitive performance against state-of-the-art baselines. It also generates query-dependent, human-readable logical rules that serve as explicit explanations for its inferences. |
| title | SLogic: Subgraph-Informed Logical Rule Learning for Knowledge Graph Completion |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2510.00279 |