# Reinforced Anytime Bottom Up Rule Learning for Knowledge Graph Completion

arXiv: https://arxiv.org/abs/2004.04412 · HTML: https://mlsanity.com/paper/2004.04412/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Apr 2020.

## Built on by (most cited first, 24 of 24)

- [TLogic: Temporal Logical Rules for Explainable Link Forecasting on Temporal Knowledge Graphs](https://mlsanity.com/paper/2112.08025/) (2021)
- [A Survey on Neural-symbolic Learning Systems](https://mlsanity.com/paper/2111.08164/) (2021)
- [Neural Multi-Hop Reasoning With Logical Rules on Biomedical Knowledge Graphs](https://mlsanity.com/paper/2103.10367/) (2021)
- [TILP: Differentiable Learning of Temporal Logical Rules on Knowledge Graphs](https://mlsanity.com/paper/2402.12309/) (2024)
- [SAFRAN: An interpretable, rule-based link prediction method outperforming embedding models](https://mlsanity.com/paper/2109.08002/) (2021)
- [ForecastTKGQuestions: A Benchmark for Temporal Question Answering and Forecasting over Temporal Knowledge Graphs](https://mlsanity.com/paper/2208.06501/) (2022)
- [GraphOracle: Efficient Fully-Inductive Knowledge Graph Reasoning via Relation-Dependency Graphs](https://mlsanity.com/paper/2505.11125/) (2025)
- [SQUIRE: A Sequence-to-sequence Framework for Multi-hop Knowledge Graph Reasoning](https://mlsanity.com/paper/2201.06206/) (2022)
- [Inductive Knowledge Graph Reasoning for Multi-batch Emerging Entities](https://mlsanity.com/paper/2208.10378/) (2022)
- [NeuSTIP: A Novel Neuro-Symbolic Model for Link and Time Prediction in Temporal Knowledge Graphs](https://mlsanity.com/paper/2305.11301/) (2023)
- [Rule Mining over Knowledge Graphs via Reinforcement Learning](https://mlsanity.com/paper/2202.10381/) (2022)
- [Mixture of Length and Pruning Experts for Knowledge Graphs Reasoning](https://mlsanity.com/paper/2507.20498/) (2025)
- [Look Globally and Reason: Two-stage Path Reasoning over Sparse Knowledge Graphs](https://mlsanity.com/paper/2407.18556/) (2024)
- [Efficient multi-relational network representation using primes](https://mlsanity.com/paper/2209.06575/) (2022)
- [From Chain to Tree: Refining Chain-like Rules into Tree-like Rules on Knowledge Graphs](https://mlsanity.com/paper/2403.05130/) (2024)
- [Geospatial Trajectory Generation via Efficient Abduction: Deployment for Independent Testing](https://mlsanity.com/paper/2407.06447/) (2024)
- [Context Pooling: Query-specific Graph Pooling for Generic Inductive Link Prediction in Knowledge Graphs](https://mlsanity.com/paper/2507.07595/) (2025)
- [OMNIA: Closing the Loop by Leveraging LLMs for Knowledge Graph Completion](https://mlsanity.com/paper/2603.11820/) (2026)
- [TRACE: Temporal Rule-Anchored Chain-of-Evidence on Knowledge Graphs for Interpretable Stock Movement Prediction](https://mlsanity.com/paper/2603.12500/) (2026)
- [On the Aggregation of Rules for Knowledge Graph Completion](https://mlsanity.com/paper/2309.00306/) (2023)
- [Mining Path Association Rules in Large Property Graphs (with Appendix)](https://mlsanity.com/paper/2408.02029/) (2024)
- [Probabilistic Circuits for Knowledge Graph Completion with Reduced Rule Sets](https://mlsanity.com/paper/2508.06706/) (2025)
- [Temporal Knowledge Graph Hyperedge Forecasting: Exploring Entity-to-Category Link Prediction](https://mlsanity.com/paper/2510.24240/) (2025)
- [StruProKGR: A Structural and Probabilistic Framework for Sparse Knowledge Graph Reasoning](https://mlsanity.com/paper/2512.12613/) (2025)

## Abstract (arXiv)

Most of todays work on knowledge graph completion is concerned with sub-symbolic approaches that focus on the concept of embedding a given graph in a low dimensional vector space. Against this trend, we propose an approach called AnyBURL that is rooted in the symbolic space. Its core algorithm is based on sampling paths, which are generalized into Horn rules. Previously published results show that the prediction quality of AnyBURL is on the same level as current state of the art with the additional benefit of offering an explanation for the predicted fact. In this paper, we are concerned with two extensions of AnyBURL. Firstly, we change AnyBURLs interpretation of rules from Theta-subsumption into Theta-subsumption under Object Identity. Secondly, we introduce reinforcement learning to better guide the sampling process. We found out that reinforcement learning helps finding more valuable rules earlier in the search process. We measure the impact of both extensions and compare the resulting approach with current state of the art approaches. Our results show that AnyBURL outperforms most sub-symbolic methods.