Systematic Abductive Reasoning via Diverse Relation Representations in Vector-symbolic Architecture

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sun, Zhong-Hua, Zhang, Ru-Yuan, Zhen, Zonglei, Wang, Da-Hui, Li, Yong-Jie, Wan, Xiaohong, You, Hongzhi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929683865534464
author Sun, Zhong-Hua
Zhang, Ru-Yuan
Zhen, Zonglei
Wang, Da-Hui
Li, Yong-Jie
Wan, Xiaohong
You, Hongzhi
author_facet Sun, Zhong-Hua
Zhang, Ru-Yuan
Zhen, Zonglei
Wang, Da-Hui
Li, Yong-Jie
Wan, Xiaohong
You, Hongzhi
contents In abstract visual reasoning, monolithic deep learning models suffer from limited interpretability and generalization, while existing neuro-symbolic approaches fall short in capturing the diversity and systematicity of attributes and relation representations. To address these challenges, we propose a Systematic Abductive Reasoning model with diverse relation representations (Rel-SAR) in Vector-symbolic Architecture (VSA) to solve Raven's Progressive Matrices (RPM). To derive attribute representations with symbolic reasoning potential, we introduce not only various types of atomic vectors that represent numeric, periodic and logical semantics, but also the structured high-dimentional representation (SHDR) for the overall Grid component. For systematic reasoning, we propose novel numerical and logical relation functions and perform rule abduction and execution in a unified framework that integrates these relation representations. Experimental results demonstrate that Rel-SAR achieves significant improvement on RPM tasks and exhibits robust out-of-distribution generalization. Rel-SAR leverages the synergy between HD attribute representations and symbolic reasoning to achieve systematic abductive reasoning with both interpretable and computable semantics.
format Preprint
id arxiv_https___arxiv_org_abs_2501_11896
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Systematic Abductive Reasoning via Diverse Relation Representations in Vector-symbolic Architecture
Sun, Zhong-Hua
Zhang, Ru-Yuan
Zhen, Zonglei
Wang, Da-Hui
Li, Yong-Jie
Wan, Xiaohong
You, Hongzhi
Artificial Intelligence
In abstract visual reasoning, monolithic deep learning models suffer from limited interpretability and generalization, while existing neuro-symbolic approaches fall short in capturing the diversity and systematicity of attributes and relation representations. To address these challenges, we propose a Systematic Abductive Reasoning model with diverse relation representations (Rel-SAR) in Vector-symbolic Architecture (VSA) to solve Raven's Progressive Matrices (RPM). To derive attribute representations with symbolic reasoning potential, we introduce not only various types of atomic vectors that represent numeric, periodic and logical semantics, but also the structured high-dimentional representation (SHDR) for the overall Grid component. For systematic reasoning, we propose novel numerical and logical relation functions and perform rule abduction and execution in a unified framework that integrates these relation representations. Experimental results demonstrate that Rel-SAR achieves significant improvement on RPM tasks and exhibits robust out-of-distribution generalization. Rel-SAR leverages the synergy between HD attribute representations and symbolic reasoning to achieve systematic abductive reasoning with both interpretable and computable semantics.
title Systematic Abductive Reasoning via Diverse Relation Representations in Vector-symbolic Architecture
topic Artificial Intelligence
url https://arxiv.org/abs/2501.11896