From Chain to Tree: Refining Chain-like Rules into Tree-like Rules on Knowledge Graphs (2403.05130v2)
Abstract: With good explanatory power and controllability, rule-based methods play an important role in many tasks such as knowledge reasoning and decision support. However, existing studies primarily focused on learning chain-like rules, which limit their semantic expressions and accurate prediction abilities. As a result, chain-like rules usually fire on the incorrect grounding values, producing inaccurate or even erroneous reasoning results. In this paper, we propose the concept of tree-like rules on knowledge graphs to expand the application scope and improve the reasoning ability of rule-based methods. Meanwhile, we propose an effective framework for refining chain-like rules into tree-like rules. Experimental comparisons on four public datasets show that the proposed framework can easily adapt to other chain-like rule induction methods and the refined tree-like rules consistently achieve better performances than chain-like rules on link prediction. The data and code of this paper can be available at https://anonymous.4open.science/r/tree-rule-E3CD/.
- Neural compositional rule learning for knowledge graph reasoning. arXiv preprint arXiv:2303.03581.
- Convolutional 2d knowledge graph embeddings. 32(1).
- Neural logic machines. arXiv preprint arXiv:1904.11694.
- AMIE: association rule mining under incomplete evidence in ontological knowledge bases. pages 413–422.
- Stanley Kok and Pedro Domingos. 2007. Statistical predicate invention. pages 433–440.
- Reinforced anytime bottom up rule learning for knowledge graph completion. arXiv preprint arXiv:2004.04412.
- Simple augmentations of logical rules for neuro-symbolic knowledge graph completion. pages 256–269.
- Scalable rule learning via learning representation. pages 2149–2155.
- Rnnlogic: Learning logic rules for reasoning on knowledge graphs.
- Knowledge graph embedding for link prediction: A comparative analysis. ACM Transactions on Knowledge Discovery from Data (TKDD), 15(2):1–49.
- Yago: a core of semantic knowledge. pages 697–706.
- Kristina Toutanova and Danqi Chen. 2015. Observed versus latent features for knowledge base and text inference. pages 57–66.
- Learning typed rules over knowledge graphs. 19(1):494–503.
- Differentiable learning of logical rules for knowledge base reasoning. Advances in neural information processing systems, 30.
- Learn to explain efficiently via neural logic inductive learning.
- Differentiable logic machines. arXiv preprint arXiv:2102.11529.