Neuro-Symbolic Forward Reasoning

TL;DR

The paper introduces NSFR, a neuro-symbolic reasoning framework combining differentiable forward-chaining with object-centric deep learning to enhance logical inference from raw data.

Contribution

It presents a novel neuro-symbolic approach that integrates differentiable forward-chaining with object-centric representations for reasoning tasks.

Findings

Effective on object-centric reasoning datasets

Outperforms existing methods in accuracy

Demonstrates versatility across 2D and 3D tasks

Abstract

Reasoning is an essential part of human intelligence and thus has been a long-standing goal in artificial intelligence research. With the recent success of deep learning, incorporating reasoning with deep learning systems, i.e., neuro-symbolic AI has become a major field of interest. We propose the Neuro-Symbolic Forward Reasoner (NSFR), a new approach for reasoning tasks taking advantage of differentiable forward-chaining using first-order logic. The key idea is to combine differentiable forward-chaining reasoning with object-centric (deep) learning. Differentiable forward-chaining reasoning computes logical entailments smoothly, i.e., it deduces new facts from given facts and rules in a differentiable manner. The object-centric learning approach factorizes raw inputs into representations in terms of objects. Thus, it allows us to provide a consistent framework to perform the forward-chaining inference from raw inputs. NSFR factorizes the raw inputs into the object-centric representations, converts them into probabilistic ground atoms, and finally performs differentiable forward-chaining inference using weighted rules for inference. Our comprehensive experimental evaluations on object-centric reasoning data sets, 2D Kandinsky patterns and 3D CLEVR-Hans, and a variety of tasks show the effectiveness and advantage of our approach.