Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
162 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

From Chain to Tree: Refining Chain-like Rules into Tree-like Rules on Knowledge Graphs (2403.05130v2)

Published 8 Mar 2024 in cs.AI

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/.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (16)
  1. Neural compositional rule learning for knowledge graph reasoning. arXiv preprint arXiv:2303.03581.
  2. Convolutional 2d knowledge graph embeddings. 32(1).
  3. Neural logic machines. arXiv preprint arXiv:1904.11694.
  4. AMIE: association rule mining under incomplete evidence in ontological knowledge bases. pages 413–422.
  5. Stanley Kok and Pedro Domingos. 2007. Statistical predicate invention. pages 433–440.
  6. Reinforced anytime bottom up rule learning for knowledge graph completion. arXiv preprint arXiv:2004.04412.
  7. Simple augmentations of logical rules for neuro-symbolic knowledge graph completion. pages 256–269.
  8. Scalable rule learning via learning representation. pages 2149–2155.
  9. Rnnlogic: Learning logic rules for reasoning on knowledge graphs.
  10. Knowledge graph embedding for link prediction: A comparative analysis. ACM Transactions on Knowledge Discovery from Data (TKDD), 15(2):1–49.
  11. Yago: a core of semantic knowledge. pages 697–706.
  12. Kristina Toutanova and Danqi Chen. 2015. Observed versus latent features for knowledge base and text inference. pages 57–66.
  13. Learning typed rules over knowledge graphs. 19(1):494–503.
  14. Differentiable learning of logical rules for knowledge base reasoning. Advances in neural information processing systems, 30.
  15. Learn to explain efficiently via neural logic inductive learning.
  16. Differentiable logic machines. arXiv preprint arXiv:2102.11529.

Summary

We haven't generated a summary for this paper yet.