A Neuro-vector-symbolic Architecture for Solving Raven's Progressive Matrices

TL;DR

This paper introduces a neuro-vector-symbolic architecture (NVSA) that combines neural and symbolic AI to effectively solve Raven's Progressive Matrices, achieving high accuracy and faster reasoning than previous methods.

Contribution

The paper presents NVSA, a novel neuro-vector-symbolic architecture that addresses the binding problem and rule search issues in neuro-symbolic AI, demonstrating superior performance on Raven's datasets.

Findings

Achieves 87.7% accuracy on RAVEN dataset

Achieves 88.1% accuracy on I-RAVEN dataset

NVSA is two orders of magnitude faster than previous neuro-symbolic approaches

Abstract

Neither deep neural networks nor symbolic AI alone has approached the kind of intelligence expressed in humans. This is mainly because neural networks are not able to decompose joint representations to obtain distinct objects (the so-called binding problem), while symbolic AI suffers from exhaustive rule searches, among other problems. These two problems are still pronounced in neuro-symbolic AI which aims to combine the best of the two paradigms. Here, we show that the two problems can be addressed with our proposed neuro-vector-symbolic architecture (NVSA) by exploiting its powerful operators on high-dimensional distributed representations that serve as a common language between neural networks and symbolic AI. The efficacy of NVSA is demonstrated by solving the Raven's progressive matrices datasets. Compared to state-of-the-art deep neural network and neuro-symbolic approaches, end-to-end training of NVSA achieves a new record of 87.7% average accuracy in RAVEN, and 88.1% in I-RAVEN datasets. Moreover, compared to the symbolic reasoning within the neuro-symbolic approaches, the probabilistic reasoning of NVSA with less expensive operations on the distributed representations is two orders of magnitude faster. Our code is available at https://github.com/IBM/neuro-vector-symbolic-architectures.