# Rule Mining over Knowledge Graphs via Reinforcement Learning

arXiv: https://arxiv.org/abs/2202.10381 · HTML: https://mlsanity.com/paper/2202.10381/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 47 references that are in the map.
- First posted on arXiv 21 Feb 2022.

## Builds on (most cited first, 18 of 18)

- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [Embedding Entities and Relations for Learning and Inference in Knowledge Bases](https://mlsanity.com/paper/1412.6575/) (2014)
- [RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space](https://mlsanity.com/paper/1902.10197/) (2019)
- [TuckER: Tensor Factorization for Knowledge Graph Completion](https://mlsanity.com/paper/1901.09590/) (2019)
- [Automatic Goal Generation for Reinforcement Learning Agents](https://mlsanity.com/paper/1705.06366/) (2017)
- [Automated Curriculum Learning for Neural Networks](https://mlsanity.com/paper/1704.03003/) (2017)
- [DRUM: End-To-End Differentiable Rule Mining On Knowledge Graphs](https://mlsanity.com/paper/1911.00055/) (2019)
- [Canonical Tensor Decomposition for Knowledge Base Completion](https://mlsanity.com/paper/1806.07297/) (2018)
- [Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Play](https://mlsanity.com/paper/1703.05407/) (2017)
- [RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphs](https://mlsanity.com/paper/2010.04029/) (2020)
- [Horizon: Facebook's Open Source Applied Reinforcement Learning Platform](https://mlsanity.com/paper/1811.00260/) (2018)
- [Learn to Explain Efficiently via Neural Logic Inductive Learning](https://mlsanity.com/paper/1910.02481/) (2019)
- [Unsupervised Curricula for Visual Meta-Reinforcement Learning](https://mlsanity.com/paper/1912.04226/) (2019)
- [Compositional Vector Space Models for Knowledge Base Completion](https://mlsanity.com/paper/1504.06662/) (2015)
- [Joint Entity Linking with Deep Reinforcement Learning](https://mlsanity.com/paper/1902.00330/) (2019)
- [Reinforced Anytime Bottom Up Rule Learning for Knowledge Graph Completion](https://mlsanity.com/paper/2004.04412/) (2020)
- [Towards Learning Instantiated Logical Rules from Knowledge Graphs](https://mlsanity.com/paper/2003.06071/) (2020)

## Built on by (most cited first, 5 of 5)

- [Comprehensible Artificial Intelligence on Knowledge Graphs: A survey](https://mlsanity.com/paper/2404.03499/) (2024)
- [Harnessing Knowledge and Reasoning for Human-Like Natural Language Generation: A Brief Review](https://mlsanity.com/paper/2212.03747/) (2022)
- [An Axiomatic Study of the Evaluation of Enthymeme Decoding in Weighted Structured Argumentation](https://mlsanity.com/paper/2411.04555/) (2024)
- [Mining Path Association Rules in Large Property Graphs (with Appendix)](https://mlsanity.com/paper/2408.02029/) (2024)
- [JAMPR+/L2D: scalable neural heuristic for constrained vehicle routing problems in dynamic environment](https://mlsanity.com/paper/2609.26275/) (2026)

## Abstract (arXiv)

Knowledge graphs (KGs) are an important source repository for a wide range of applications and rule mining from KGs recently attracts wide research interest in the KG-related research community. Many solutions have been proposed for the rule mining from large-scale KGs, which however are limited in the inefficiency of rule generation and ineffectiveness of rule evaluation. To solve these problems, in this paper we propose a generation-then-evaluation rule mining approach guided by reinforcement learning. Specifically, a two-phased framework is designed. The first phase aims to train a reinforcement learning agent for rule generation from KGs, and the second is to utilize the value function of the agent to guide the step-by-step rule generation. We conduct extensive experiments on several datasets and the results prove that our rule mining solution achieves state-of-the-art performance in terms of efficiency and effectiveness.