A Neuro-symbolic Framework under Statistical Relational Learning

Neuro-symbolic systems aim to combine neural learning with symbolic reasoning for building interpretable and generalizable intelligent systems. While recent studies have explored different strategies for neuro-symbolic integration, existing approaches remain limited by (i) the absence of unified learning mechanisms between continuous neural representations and discrete symbolic concepts, (ii) weak interaction between neural prediction and symbolic reasoning, and (iii) restricted reuse of learned concepts for unseen reasoning scenarios. To address these issues, we propose NSF-SRL, a general neuro-symbolic framework based on statistical relational learning. NSF-SRL jointly models neural predictions, latent predicates and first-order logic rules within a unified probabilistic framework. For concept learning, NSF-SRL introduces a neuralized variational inference mechanism that learns predicate-level representations from neural representations and enables efficient neuro-symbolic interaction through variational expectation-maximization optimization. For concept manipulation, NSF-SRL allows learned concepts to be reused and composed with logic rules for interpretable explanation and compositional reasoning. Extensive experiments on digit image addition, zero-shot image classification and visual relationship detection, together with comprehensive analyses, demonstrate the effectiveness, generalization and scalability of NSF-SRL.

Authors

Institutions

Publication Details

Journal
IEEE Transactions on Pattern Analysis and Machine Intelligence
Published
2026-11-17
DOI
https://doi.org/10.1109/tpami.2026.3755075
Primary Topic
Logic, Reasoning, and Knowledge
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

A Neuro-symbolic Framework under Statistical Relational Learning

Shirui Pan, Bo Xiong Yang, Xueyan Liu, Dongran Yu et al.
1 links
IEEE Transactions on Pattern Analysis and Machine Intelligence
Logic, Reasoning, and Knowledge
article

A Neuro-symbolic Framework under Statistical Relational Learning

Shirui Pan, Bo Xiong Yang, Xueyan Liu, Dongran Yu, Anchen Li
article en

Abstract

Neuro-symbolic systems aim to combine neural learning with symbolic reasoning for building interpretable and generalizable intelligent systems. While recent studies have explored different strategies for neuro-symbolic integration, existing approaches remain limited by (i) the absence of unified learning mechanisms between continuous neural representations and discrete symbolic concepts, (ii) weak interaction between neural prediction and symbolic reasoning, and (iii) restricted reuse of learned concepts for unseen reasoning scenarios. To address these issues, we propose NSF-SRL, a general neuro-symbolic framework based on statistical relational learning. NSF-SRL jointly models neural predictions, latent predicates and first-order logic rules within a unified probabilistic framework. For concept learning, NSF-SRL introduces a neuralized variational inference mechanism that learns predicate-level representations from neural representations and enables efficient neuro-symbolic interaction through variational expectation-maximization optimization. For concept manipulation, NSF-SRL allows learned concepts to be reused and composed with logic rules for interpretable explanation and compositional reasoning. Extensive experiments on digit image addition, zero-shot image classification and visual relationship detection, together with comprehensive analyses, demonstrate the effectiveness, generalization and scalability of NSF-SRL.

IEEE Transactions on Pattern Analysis and Machine IntelligenceVol. PP
Griffith University (AU), Jilin University (CN)
Logic, Reasoning, and Knowledge
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon