Abstract Reasoning via Logic-guided Generation

TL;DR

This paper introduces LoGe, a logic-guided generative framework for abstract reasoning that models reasoning as an optimization in propositional logic, outperforming traditional neural networks on the RAVEN benchmark.

Contribution

It proposes a novel logic-guided generative approach for abstract reasoning, bridging the gap between human-like reasoning and neural network methods.

Findings

LoGe outperforms black box DNNs on RAVEN benchmark.

It effectively captures rules of various attributes from observations.

The framework demonstrates improved reasoning accuracy.

Abstract

Abstract reasoning, i.e., inferring complicated patterns from given observations, is a central building block of artificial general intelligence. While humans find the answer by either eliminating wrong candidates or first constructing the answer, prior deep neural network (DNN)-based methods focus on the former discriminative approach. This paper aims to design a framework for the latter approach and bridge the gap between artificial and human intelligence. To this end, we propose logic-guided generation (LoGe), a novel generative DNN framework that reduces abstract reasoning as an optimization problem in propositional logic. LoGe is composed of three steps: extract propositional variables from images, reason the answer variables with a logic layer, and reconstruct the answer image from the variables. We demonstrate that LoGe outperforms the black box DNN frameworks for generative abstract reasoning under the RAVEN benchmark, i.e., reconstructing answers based on capturing correct rules of various attributes from observations.