# Learning Reasoning Strategies in End-to-End Differentiable Proving

arXiv: https://arxiv.org/abs/2007.06477 · HTML: https://mlsanity.com/paper/2007.06477/

## Key facts

- Cited by 60 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jul 2020.

## Built on by (most cited first, 30 of 60)

- [A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity](https://mlsanity.com/paper/2302.04023/) (2023)
- [From Statistical Relational to Neurosymbolic Artificial Intelligence: a Survey](https://mlsanity.com/paper/2108.11451/) (2021)
- [Large Language Models can Learn Rules](https://mlsanity.com/paper/2310.07064/) (2023)
- [Are Large Language Models Really Good Logical Reasoners? A Comprehensive Evaluation and Beyond](https://mlsanity.com/paper/2306.09841/) (2023)
- [Scallop: A Language for Neurosymbolic Programming](https://mlsanity.com/paper/2304.04812/) (2023)
- [Coupling Large Language Models with Logic Programming for Robust and General Reasoning from Text](https://mlsanity.com/paper/2307.07696/) (2023)
- [Neuro-Symbolic Artificial Intelligence: Current Trends](https://mlsanity.com/paper/2105.05330/) (2021)
- [Systematic Generalization with Edge Transformers](https://mlsanity.com/paper/2112.00578/) (2021)
- [Neuro-Symbolic Inductive Logic Programming with Logical Neural Networks](https://mlsanity.com/paper/2112.03324/) (2021)
- [Towards Data-and Knowledge-Driven Artificial Intelligence: A Survey on Neuro-Symbolic Computing](https://mlsanity.com/paper/2210.15889/) (2022)
- [VAEL: Bridging Variational Autoencoders and Probabilistic Logic Programming](https://mlsanity.com/paper/2202.04178/) (2022)
- [Neural Multi-Hop Reasoning With Logical Rules on Biomedical Knowledge Graphs](https://mlsanity.com/paper/2103.10367/) (2021)
- [Complex Query Answering on Eventuality Knowledge Graph with Implicit Logical Constraints](https://mlsanity.com/paper/2305.19068/) (2023)
- [A Survey of Trustworthy Graph Learning: Reliability, Explainability, and Privacy Protection](https://mlsanity.com/paper/2205.10014/) (2022)
- [Neural Compositional Rule Learning for Knowledge Graph Reasoning](https://mlsanity.com/paper/2303.03581/) (2023)
- [Quantifying the Capabilities of LLMs across Scale and Precision](https://mlsanity.com/paper/2405.03146/) (2024)
- [Knowledge Graph Reasoning with Logics and Embeddings: Survey and Perspective](https://mlsanity.com/paper/2202.07412/) (2022)
- [Logical Reasoning with Span-Level Predictions for Interpretable and Robust NLI Models](https://mlsanity.com/paper/2205.11432/) (2022)
- [Improved Logical Reasoning of Language Models via Differentiable Symbolic Programming](https://mlsanity.com/paper/2305.03742/) (2023)
- [FF-NSL: Feed-Forward Neural-Symbolic Learner](https://mlsanity.com/paper/2106.13103/) (2021)
- [A Survey on Compositional Learning of AI Models: Theoretical and Experimental Practices](https://mlsanity.com/paper/2406.08787/) (2024)
- [Sequential Query Encoding For Complex Query Answering on Knowledge Graphs](https://mlsanity.com/paper/2302.13114/) (2023)
- [Learning Differentiable Logic Programs for Abstract Visual Reasoning](https://mlsanity.com/paper/2307.00928/) (2023)
- [Is Multi-Hop Reasoning Really Explainable? Towards Benchmarking Reasoning Interpretability](https://mlsanity.com/paper/2104.06751/) (2021)
- [Learning with Logical Constraints but without Shortcut Satisfaction](https://mlsanity.com/paper/2403.00329/) (2024)
- [DeiSAM: Segment Anything with Deictic Prompting](https://mlsanity.com/paper/2402.14123/) (2024)
- [Certified Deductive Reasoning with Language Models](https://mlsanity.com/paper/2306.04031/) (2023)
- [Combining Rules and Embeddings via Neuro-Symbolic AI for Knowledge Base Completion](https://mlsanity.com/paper/2109.09566/) (2021)
- [A Critical Review of Inductive Logic Programming Techniques for Explainable AI](https://mlsanity.com/paper/2112.15319/) (2021)
- [R5: Rule Discovery with Reinforced and Recurrent Relational Reasoning](https://mlsanity.com/paper/2205.06454/) (2022)

## Abstract (arXiv)

Attempts to render deep learning models interpretable, data-efficient, and robust have seen some success through hybridisation with rule-based systems, for example, in Neural Theorem Provers (NTPs). These neuro-symbolic models can induce interpretable rules and learn representations from data via back-propagation, while providing logical explanations for their predictions. However, they are restricted by their computational complexity, as they need to consider all possible proof paths for explaining a goal, thus rendering them unfit for large-scale applications. We present Conditional Theorem Provers (CTPs), an extension to NTPs that learns an optimal rule selection strategy via gradient-based optimisation. We show that CTPs are scalable and yield state-of-the-art results on the CLUTRR dataset, which tests systematic generalisation of neural models by learning to reason over smaller graphs and evaluating on larger ones. Finally, CTPs show better link prediction results on standard benchmarks in comparison with other neural-symbolic models, while being explainable. All source code and datasets are available online, at https://github.com/uclnlp/ctp.