Unsupervised Contrastive Graph Kolmogorov–Arnold Networks Enhanced Cross-Modal Retrieval Hashing

To address modality heterogeneity and accelerate large-scale retrieval, cross-modal hashing strategies generate compact binary codes that enhance computational efficiency. Existing approaches often struggle with suboptimal feature learning due to fixed activation functions and limited cross-modal in...

Full description

Saved in:
Bibliographic Details
Main Authors: Hongyu Lin, Shaofeng Shen, Yuchen Zhang, Renwei Xia
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Mathematics
Subjects:
Online Access:https://www.mdpi.com/2227-7390/13/11/1880
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850160793075580928
author Hongyu Lin
Shaofeng Shen
Yuchen Zhang
Renwei Xia
author_facet Hongyu Lin
Shaofeng Shen
Yuchen Zhang
Renwei Xia
author_sort Hongyu Lin
collection DOAJ
description To address modality heterogeneity and accelerate large-scale retrieval, cross-modal hashing strategies generate compact binary codes that enhance computational efficiency. Existing approaches often struggle with suboptimal feature learning due to fixed activation functions and limited cross-modal interaction. We propose Unsupervised Contrastive Graph Kolmogorov–Arnold Networks (GraphKAN) Enhanced Cross-modal Retrieval Hashing (UCGKANH), integrating GraphKAN with contrastive learning and hypergraph-based enhancement. GraphKAN enables more flexible cross-modal representation through enhanced nonlinear expression of features. We introduce contrastive learning that captures modality-invariant structures through sample pairs. To preserve high-order semantic relations, we construct a hypergraph-based information propagation mechanism, refining hash codes by enforcing global consistency. The efficacy of our UCGKANH approach is validated by thorough tests on the MIR-FLICKR, NUS-WIDE, and MS COCO datasets, which show significant gains in retrieval accuracy coupled with strong computational efficiency.
format Article
id doaj-art-3947e4f6602f4c9ba10e55d1d45f3e64
institution OA Journals
issn 2227-7390
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Mathematics
spelling doaj-art-3947e4f6602f4c9ba10e55d1d45f3e642025-08-20T02:23:04ZengMDPI AGMathematics2227-73902025-06-011311188010.3390/math13111880Unsupervised Contrastive Graph Kolmogorov–Arnold Networks Enhanced Cross-Modal Retrieval HashingHongyu Lin0Shaofeng Shen1Yuchen Zhang2Renwei Xia3Dundee International Institute of Central South University, Central South University, Changsha 410083, ChinaSchool of Computer Science and Engineering, Central South University, Changsha 410083, ChinaSchool of Computer Science and Engineering, Central South University, Changsha 410083, ChinaSchool of Computer Science and Engineering, Central South University, Changsha 410083, ChinaTo address modality heterogeneity and accelerate large-scale retrieval, cross-modal hashing strategies generate compact binary codes that enhance computational efficiency. Existing approaches often struggle with suboptimal feature learning due to fixed activation functions and limited cross-modal interaction. We propose Unsupervised Contrastive Graph Kolmogorov–Arnold Networks (GraphKAN) Enhanced Cross-modal Retrieval Hashing (UCGKANH), integrating GraphKAN with contrastive learning and hypergraph-based enhancement. GraphKAN enables more flexible cross-modal representation through enhanced nonlinear expression of features. We introduce contrastive learning that captures modality-invariant structures through sample pairs. To preserve high-order semantic relations, we construct a hypergraph-based information propagation mechanism, refining hash codes by enforcing global consistency. The efficacy of our UCGKANH approach is validated by thorough tests on the MIR-FLICKR, NUS-WIDE, and MS COCO datasets, which show significant gains in retrieval accuracy coupled with strong computational efficiency.https://www.mdpi.com/2227-7390/13/11/1880cross-modal retrievalhashingGraph Kolmogorov–Arnold Networkscontrastive learninghypergraph neural networks
spellingShingle Hongyu Lin
Shaofeng Shen
Yuchen Zhang
Renwei Xia
Unsupervised Contrastive Graph Kolmogorov–Arnold Networks Enhanced Cross-Modal Retrieval Hashing
Mathematics
cross-modal retrieval
hashing
Graph Kolmogorov–Arnold Networks
contrastive learning
hypergraph neural networks
title Unsupervised Contrastive Graph Kolmogorov–Arnold Networks Enhanced Cross-Modal Retrieval Hashing
title_full Unsupervised Contrastive Graph Kolmogorov–Arnold Networks Enhanced Cross-Modal Retrieval Hashing
title_fullStr Unsupervised Contrastive Graph Kolmogorov–Arnold Networks Enhanced Cross-Modal Retrieval Hashing
title_full_unstemmed Unsupervised Contrastive Graph Kolmogorov–Arnold Networks Enhanced Cross-Modal Retrieval Hashing
title_short Unsupervised Contrastive Graph Kolmogorov–Arnold Networks Enhanced Cross-Modal Retrieval Hashing
title_sort unsupervised contrastive graph kolmogorov arnold networks enhanced cross modal retrieval hashing
topic cross-modal retrieval
hashing
Graph Kolmogorov–Arnold Networks
contrastive learning
hypergraph neural networks
url https://www.mdpi.com/2227-7390/13/11/1880
work_keys_str_mv AT hongyulin unsupervisedcontrastivegraphkolmogorovarnoldnetworksenhancedcrossmodalretrievalhashing
AT shaofengshen unsupervisedcontrastivegraphkolmogorovarnoldnetworksenhancedcrossmodalretrievalhashing
AT yuchenzhang unsupervisedcontrastivegraphkolmogorovarnoldnetworksenhancedcrossmodalretrievalhashing
AT renweixia unsupervisedcontrastivegraphkolmogorovarnoldnetworksenhancedcrossmodalretrievalhashing