Abstract Reasoning via Logic-guided Generation
Sihyun Yu, Sangwoo Mo, Sungsoo Ahn, Jinwoo Shin
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.