GOMFuNet: A Geometric Orthogonal Multimodal Fusion Network for Enhanced Prediction Reliability

Integrating information from heterogeneous data sources poses significant mathematical challenges, particularly in ensuring the reliability and reducing the uncertainty of predictive models. This paper introduces the Geometric Orthogonal Multimodal Fusion Network (GOMFuNet), a novel mathematical fra...

Full description

Saved in:
Bibliographic Details
Main Authors: Yi Guo, Rui Zhong
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Mathematics
Subjects:
Online Access:https://www.mdpi.com/2227-7390/13/11/1791
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849331088550264832
author Yi Guo
Rui Zhong
author_facet Yi Guo
Rui Zhong
author_sort Yi Guo
collection DOAJ
description Integrating information from heterogeneous data sources poses significant mathematical challenges, particularly in ensuring the reliability and reducing the uncertainty of predictive models. This paper introduces the Geometric Orthogonal Multimodal Fusion Network (GOMFuNet), a novel mathematical framework designed to address these challenges. GOMFuNet synergistically combines two core mathematical principles: (1) It utilizes geometric deep learning, specifically Graph Convolutional Networks (GCNs), within its Cross-Modal Label Fusion Module (CLFM) to perform fusion in a high-level semantic label space, thereby preserving inter-sample topological relationships and enhancing robustness to inconsistencies. (2) It incorporates a novel Label Confidence Learning Module (LCLM) derived from optimization theory, which explicitly enhances prediction reliability by enforcing mathematical orthogonality among the predicted class probability vectors, directly minimizing output uncertainty. We demonstrate GOMFuNet’s effectiveness through comprehensive experiments, including confidence calibration analysis and robustness tests, and validate its practical utility via a case study on educational performance prediction using structured, textual, and audio data. Results show GOMFuNet achieves significantly improved performance (90.17% classification accuracy, 88.03% R<sup>2</sup> regression) and enhanced reliability compared to baseline and state-of-the-art multimodal methods, validating its potential as a robust framework for reliable multimodal learning.
format Article
id doaj-art-5a048c650bbb4d8c8396ba2eb7e95b38
institution Kabale University
issn 2227-7390
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Mathematics
spelling doaj-art-5a048c650bbb4d8c8396ba2eb7e95b382025-08-20T03:46:43ZengMDPI AGMathematics2227-73902025-05-011311179110.3390/math13111791GOMFuNet: A Geometric Orthogonal Multimodal Fusion Network for Enhanced Prediction ReliabilityYi Guo0Rui Zhong1School of Economics, Beijing Technology and Business University, Beijing 102401, ChinaInformation Initiative Center, Hokkaido University, Sapporo 060-0808, JapanIntegrating information from heterogeneous data sources poses significant mathematical challenges, particularly in ensuring the reliability and reducing the uncertainty of predictive models. This paper introduces the Geometric Orthogonal Multimodal Fusion Network (GOMFuNet), a novel mathematical framework designed to address these challenges. GOMFuNet synergistically combines two core mathematical principles: (1) It utilizes geometric deep learning, specifically Graph Convolutional Networks (GCNs), within its Cross-Modal Label Fusion Module (CLFM) to perform fusion in a high-level semantic label space, thereby preserving inter-sample topological relationships and enhancing robustness to inconsistencies. (2) It incorporates a novel Label Confidence Learning Module (LCLM) derived from optimization theory, which explicitly enhances prediction reliability by enforcing mathematical orthogonality among the predicted class probability vectors, directly minimizing output uncertainty. We demonstrate GOMFuNet’s effectiveness through comprehensive experiments, including confidence calibration analysis and robustness tests, and validate its practical utility via a case study on educational performance prediction using structured, textual, and audio data. Results show GOMFuNet achieves significantly improved performance (90.17% classification accuracy, 88.03% R<sup>2</sup> regression) and enhanced reliability compared to baseline and state-of-the-art multimodal methods, validating its potential as a robust framework for reliable multimodal learning.https://www.mdpi.com/2227-7390/13/11/1791multimodal integrationuncertainty quantificationlearning resource optimizationcrossmodal mappingconfidence calibrationeducational sustainability
spellingShingle Yi Guo
Rui Zhong
GOMFuNet: A Geometric Orthogonal Multimodal Fusion Network for Enhanced Prediction Reliability
Mathematics
multimodal integration
uncertainty quantification
learning resource optimization
crossmodal mapping
confidence calibration
educational sustainability
title GOMFuNet: A Geometric Orthogonal Multimodal Fusion Network for Enhanced Prediction Reliability
title_full GOMFuNet: A Geometric Orthogonal Multimodal Fusion Network for Enhanced Prediction Reliability
title_fullStr GOMFuNet: A Geometric Orthogonal Multimodal Fusion Network for Enhanced Prediction Reliability
title_full_unstemmed GOMFuNet: A Geometric Orthogonal Multimodal Fusion Network for Enhanced Prediction Reliability
title_short GOMFuNet: A Geometric Orthogonal Multimodal Fusion Network for Enhanced Prediction Reliability
title_sort gomfunet a geometric orthogonal multimodal fusion network for enhanced prediction reliability
topic multimodal integration
uncertainty quantification
learning resource optimization
crossmodal mapping
confidence calibration
educational sustainability
url https://www.mdpi.com/2227-7390/13/11/1791
work_keys_str_mv AT yiguo gomfunetageometricorthogonalmultimodalfusionnetworkforenhancedpredictionreliability
AT ruizhong gomfunetageometricorthogonalmultimodalfusionnetworkforenhancedpredictionreliability