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

Source: [Learning Reasoning Strategies in End-to-End Differentiable Proving](<https://www.sota2.com/research/paper/68fa68351e209131cea1accd>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T03:18:34.140Z

Authors: Pasquale Minervini, Sebastian Riedel, Pontus Stenetorp, Edward Grefenstette, Tim Rockt\\"aschel

Published: 2020-07-13T16:22:14.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Link Prediction on Nations](<https://www.sota2.com/research/sota/link-prediction-on-nations.md>): Link Prediction; Nations; MRR: 0.709.

- [Link Prediction on Countries S1](<https://www.sota2.com/research/sota/link-prediction-on-countries-s1.md>): Link Prediction; Countries S1; AUC-PR: 1.

- [Link Prediction on Countries S3](<https://www.sota2.com/research/sota/link-prediction-on-countries-s3.md>): Link Prediction; Countries S3; AUC-PR: 0.9478.

- [Link Prediction on Kinship](<https://www.sota2.com/research/sota/link-prediction-on-kinship.md>): Link Prediction; Kinship; MRR: 0.764.

- [Link Prediction on Countries S2](<https://www.sota2.com/research/sota/link-prediction-on-countries-s2.md>): Link Prediction; Countries S2; AUC-PR: 91.81.

- [Link Prediction on UMLS](<https://www.sota2.com/research/sota/link-prediction-on-umls.md>): Link Prediction; UMLS; Hits@10: 98.4.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2007.06477>)

[PDF](<https://arxiv.org/pdf/2007.06477.pdf>)

[Implementation](<https://github.com/uclnlp/ctp>)