Abductive Logical Reasoning on Knowledge Graphs

Jiaxin Bai, Yicheng Wang, Tianshi Zheng, Yue Guo, Xin Liu, Yangqiu SongOpenReview 2024 · Submission to ICLR 2024 · Rejected · OpenReview

Abstract

Abductive reasoning is logical reasoning that makes educated guesses to infer the most likely reasons to explain the observations. However, the abductive logical reasoning over knowledge graphs (KGs) is underexplored in KG literature. In this paper, we initially and formally raise the task of abductive logical reasoning over KGs, which involves inferring the most probable logic hypothesis from the KGs to explain an observed entity set. Traditional approaches use symbolic methods, like searching, to tackle the knowledge graph problem. However, the symbolic methods are unsuitable for this task, because the KGs are naturally incomplete, and the logical hypotheses can be complex with multiple variables and relations. To address these issues, we propose a generative approach to create logical expres- sions based on observations. First, we sample hypothesis-observation pairs from the KG and use supervised training to train a generative model that generates hy- potheses from observations. Since supervised learning only minimizes structural differences between generated and reference hypotheses, higher structural similar- ity does not guarantee a better explanation for observations. To tackle this issue, we introduce the Reinforcement Learning from the Knowledge Graph (RLF-KG) method, which minimizes the differences between observations and conclusions drawn from the generated hypotheses according to the KG. Experimental results demonstrate that transformer-based generative models can generate logical expla- nations robustly and efficiently. Moreover, with the assistance of RLF-KG, the generated hypothesis can provide better explanations for the observations, and the method of supervised learning with RLF-KG achieves state-of-the-art results on abductive knowledge graph reasoning on three widely used KGs.
BibTeX
@misc{bai2024abductive,
  author = {Jiaxin Bai and Yicheng Wang and Tianshi Zheng and Yue Guo and Xin Liu and Yangqiu Song},
  title = {{Abductive Logical Reasoning on Knowledge Graphs}},
  year = {2024},
  url = {https://openreview.net/forum?id=DIuSX4HqDZ},
  howpublished = {OpenReview},
  note = {Submitted to ICLR 2024},
}
Figure