pix2rule: End-to-end Neuro-symbolic Rule Learning

Code

• github.com/nuric/pix2rule
  OfficialIn papertf★ 12
• github.com/kittykg/neural-dnf-cub
  pytorch★ 6
• github.com/kittykg/neural-dnf-tmc
  pytorch★ 3

Abstract

Humans have the ability to seamlessly combine low-level visual input with high-level symbolic reasoning often in the form of recognising objects, learning relations between them and applying rules. Neuro-symbolic systems aim to bring a unifying approach to connectionist and logic-based principles for visual processing and abstract reasoning respectively. This paper presents a complete neuro-symbolic method for processing images into objects, learning relations and logical rules in an end-to-end fashion. The main contribution is a differentiable layer in a deep learning architecture from which symbolic relations and rules can be extracted by pruning and thresholding. We evaluate our model using two datasets: subgraph isomorphism task for symbolic rule learning and an image classification domain with compound relations for learning objects, relations and rules. We demonstrate that our model scales beyond state-of-the-art symbolic learners and outperforms deep relational neural network architectures.

Tasks

Reproductions