Perform Like an Engine: A Closed-Loop Neural-Symbolic Learning Framework for Knowledge Graph Inference
This work addresses the problem of knowledge graph inference for applications requiring both accuracy and interpretability, representing an incremental improvement by hybridizing existing methods.
The paper tackles the incompleteness of knowledge graphs by proposing a closed-loop neural-symbolic learning framework called EngineKG, which combines knowledge graph embedding and rule learning modules to improve efficiency, generalization, and interpretability; experimental results on four real-world datasets show it outperforms baselines on link prediction tasks.
Knowledge graph (KG) inference aims to address the natural incompleteness of KGs, including rule learning-based and KG embedding (KGE) models. However, the rule learning-based models suffer from low efficiency and generalization while KGE models lack interpretability. To address these challenges, we propose a novel and effective closed-loop neural-symbolic learning framework EngineKG via incorporating our developed KGE and rule learning modules. KGE module exploits symbolic rules and paths to enhance the semantic association between entities and relations for improving KG embeddings and interpretability. A novel rule pruning mechanism is proposed in the rule learning module by leveraging paths as initial candidate rules and employing KG embeddings together with concepts for extracting more high-quality rules. Experimental results on four real-world datasets show that our model outperforms the relevant baselines on link prediction tasks, demonstrating the superiority of our KG inference model in a neural-symbolic learning fashion.