The University of Southampton
University of Southampton Institutional Repository

Label enhancement via manifold approximation and projection with graph convolutional network

Label enhancement via manifold approximation and projection with graph convolutional network
Label enhancement via manifold approximation and projection with graph convolutional network
Label enhancement (LE) aims to enrich logical labels into their corresponding label distributions. But existing LE algorithms fail to fully leverage the structural information in the feature space to improve LE learning. To address this key issue, we first apply manifold learning to map the relatedness between low-dimensional feature samples to the label space. Based on the smoothness assumption of manifolds, the implicit correlation between low-dimensional feature and label spaces effectively promotes the LE process, enabling the learning model to accurately capture the mapping relationship between feature and label manifolds. This leads to an LE based on feature representation (LEFR) algorithm. We also propose an LE algorithm based on graph convolutional network (GCN), called LE-GCN. Inspired by the relationship between threshold connections and label connections, we extend GCN to the LE field for the first time to fully exploit the hidden relationships between nodes and labels. By enhancing node information with threshold connections and label connections, the label learning accuracy reaches a new level. Experiments on real-world datasets show that our LEFR and LE-GCN outperform several state-of-the-art LE algorithms.
Graph convolutional network, Label distribution learning, Manifold learning, Multi-label classification, Robust linear regression
0031-3203
Tan, Chao
c465770b-c23e-482d-97f9-9856b3f52c74
Chen, Sheng
9310a111-f79a-48b8-98c7-383ca93cbb80
Geng, Xin
8285685e-9bd5-47a4-88f1-9ef09781e00f
Zhou, Yunyao
1db46035-331d-4d7f-9c1e-866fbce1a4bb
Ji, Genlin
07169d5f-af46-4778-835d-d292432686a3
et al.
Tan, Chao
c465770b-c23e-482d-97f9-9856b3f52c74
Chen, Sheng
9310a111-f79a-48b8-98c7-383ca93cbb80
Geng, Xin
8285685e-9bd5-47a4-88f1-9ef09781e00f
Zhou, Yunyao
1db46035-331d-4d7f-9c1e-866fbce1a4bb
Ji, Genlin
07169d5f-af46-4778-835d-d292432686a3

Tan, Chao, Chen, Sheng and Geng, Xin , et al. (2024) Label enhancement via manifold approximation and projection with graph convolutional network. Pattern Recognition, 152, [110447]. (doi:10.1016/j.patcog.2024.110447).

Record type: Article

Abstract

Label enhancement (LE) aims to enrich logical labels into their corresponding label distributions. But existing LE algorithms fail to fully leverage the structural information in the feature space to improve LE learning. To address this key issue, we first apply manifold learning to map the relatedness between low-dimensional feature samples to the label space. Based on the smoothness assumption of manifolds, the implicit correlation between low-dimensional feature and label spaces effectively promotes the LE process, enabling the learning model to accurately capture the mapping relationship between feature and label manifolds. This leads to an LE based on feature representation (LEFR) algorithm. We also propose an LE algorithm based on graph convolutional network (GCN), called LE-GCN. Inspired by the relationship between threshold connections and label connections, we extend GCN to the LE field for the first time to fully exploit the hidden relationships between nodes and labels. By enhancing node information with threshold connections and label connections, the label learning accuracy reaches a new level. Experiments on real-world datasets show that our LEFR and LE-GCN outperform several state-of-the-art LE algorithms.

Text
A-pr3-R1 - Accepted Manuscript
Restricted to Repository staff only until 24 March 2026.
Request a copy

More information

Accepted/In Press date: 20 March 2024
e-pub ahead of print date: 24 March 2024
Published date: August 2024
Additional Information: Publisher Copyright: © 2024 Elsevier Ltd
Keywords: Graph convolutional network, Label distribution learning, Manifold learning, Multi-label classification, Robust linear regression

Identifiers

Local EPrints ID: 488538
URI: http://eprints.soton.ac.uk/id/eprint/488538
ISSN: 0031-3203
PURE UUID: de804e1a-2c6e-4af5-8bf9-b0a73b6b4da8

Catalogue record

Date deposited: 26 Mar 2024 17:46
Last modified: 22 May 2024 16:39

Export record

Altmetrics

Contributors

Author: Chao Tan
Author: Sheng Chen
Author: Xin Geng
Author: Yunyao Zhou
Author: Genlin Ji
Corporate Author: et al.

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×