Probabilistic Abduction for Visual Abstract Reasoning via Learning Rules in Vector-symbolic Architectures
This addresses the challenge of replicating human abstract reasoning in AI, with incremental improvements in efficiency and interpretability for visual reasoning tasks.
The study tackled the problem of solving Raven's progressive matrices for visual abstract reasoning by learning rule formulations in vector-symbolic architectures with just one training pass, achieving accurate predictions on in-distribution data and strong out-of-distribution performance that significantly outperformed connectionist baselines.
Abstract reasoning is a cornerstone of human intelligence, and replicating it with artificial intelligence (AI) presents an ongoing challenge. This study focuses on efficiently solving Raven's progressive matrices (RPM), a visual test for assessing abstract reasoning abilities, by using distributed computation and operators provided by vector-symbolic architectures (VSA). Instead of hard-coding the rule formulations associated with RPMs, our approach can learn the VSA rule formulations (hence the name Learn-VRF) with just one pass through the training data. Yet, our approach, with compact parameters, remains transparent and interpretable. Learn-VRF yields accurate predictions on I-RAVEN's in-distribution data, and exhibits strong out-of-distribution capabilities concerning unseen attribute-rule pairs, significantly outperforming pure connectionist baselines including large language models. Our code is available at https://github.com/IBM/learn-vector-symbolic-architectures-rule-formulations.