• Home
  • Search
  • Leveraging Graph Convolutional Networks for Semi-supervised Learning in Multi-view Non-graph Data
  • Cite Icon5
  • https://doi.org/10.1007/s12559-025-10428-yCopy DOI Icon

Leveraging Graph Convolutional Networks for Semi-supervised Learning in Multi-view Non-graph Data

Show More
  • Abstract
  • Highlights & Summary
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Semi-supervised learning with a graph-based approach has gained prominence in machine learning, particularly in scenarios where labeling data involves substantial costs. Graph convolution networks (GCNs) have found widespread application in semi-supervised learning, predominantly on graph-structured data such as citation and social networks. However, a noticeable gap exists in the application of these methods to non-graph multi-view data, such as collections of images. In an effort to address this gap, we introduce two innovative deep semi-supervised multi-view classification models specifically tailored for non-graph data. Both models share a common architecture, leveraging GCNs and integrating a label smoothing constraint. The primary distinction lies in the construction of the consensus similarity graph. The first model directly reconstructs the consensus graph from different views using a specialized objective function designed for flexible graph-based semi-supervised classification. In contrast, the second model independently reconstructs individual graphs and subsequently adaptively merges them into a unified consensus graph. Our experiments encompass various multiple-view image datasets. The results consistently demonstrate the superior performance of our proposed approach compared to traditional fusion methods with GCNs. In this research, we present two approaches for tackling semi-supervised classification challenges involving multiple views. One method is named Semi-supervised Classification with a Unified Graph (SCUG), and the other is referred to as Semi-supervised Classification with a Fused Graph (SC-Fused). Both methods share a common semi-supervised classification process, utilizing the GCN framework and incorporating label smoothing. However, the key distinction lies in the construction of the similarity graph. Unlike traditional ad hoc graph construction approaches, our proposed methods, SCUG and SC-Fused, estimate the unified graph or individual graphs, respectively, alongside the labels. This results in more optimized graphs that benefit from data smoothing and the semi-supervised context.

Loading PDF

Similar Papers
  • Research Article
  • Citations24

Sample-weighted fused graph-based semi-supervised learning on multi-view data

  • Dec 05, 2023
  • Information Fusion
  • Jingjun Bi +1
  • Research Article
  • Citations38

Joint learning of feature and topology for multi-view graph convolutional network

  • Sep 12, 2023
  • Neural Networks
  • Yuhong Chen +4
  • Dissertation

Semi-supervised learning approaches with applications in Medicinal Chemistry

  • Jan 01, 2019
  • Jadson Castro Gertrudes
  • Research Article
  • Citations18

Dynamic Graph Learning Convolutional Networks for Semi-supervised Classification

  • Jan 31, 2021
  • ACM Transactions on Multimedia Computing, Communications, and Applications
  • Sichao Fu +5
  • PDF
  • Research Article
  • Citations2

FairSwiRL: fair semi-supervised classification with representation learning

  • Jun 27, 2023
  • Machine Learning
  • Shuyi Yang +4
  • Book Chapter

Simplifying Graph Convolutional Networks as Matrix Factorization

  • Jan 01, 2021
  • Qiang Liu +2
  • Research Article
  • Citations63

A new graph-based semi-supervised method for surface defect classification

  • Nov 01, 2020
  • Robotics and Computer-Integrated Manufacturing
  • Yucheng Wang +3
  • Research Article
  • Citations4

Evaluation of a Binary Semi-supervised Classification Technique for Probabilistic Record Linkage.

  • Jan 01, 2016
  • Methods of Information in Medicine
  • J Stausberg +1
  • PDF
  • Research Article
  • Citations14

Semi-Supervised Tree Species Classification for Multi-Source Remote Sensing Images Based on a Graph Convolutional Neural Network

  • Jun 11, 2023
  • Forests
  • Xueliang Wang +3
  • Conference Article
  • Citations2

Towards Better Semi-Supervised Classification of Malicious Software

  • Mar 04, 2015
  • Shobhit Shakya +1
  • Conference Article

Multi-Channel Fusion Graph Convolutional Networks with pseudo-label for Semi-Supervised Node Classification

  • Jan 01, 2025
  • Guang Yang
  • Conference Article
  • Citations19

GraFeHTy: Graph Neural Network using Federated Learning for Human Activity Recognition

  • Dec 01, 2021
  • Abhishek Sarkar +2
  • Research Article
  • Citations106

Co-Embedding of Nodes and Edges With Graph Neural Networks.

  • Oct 14, 2020
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Xiaodong Jiang +3
  • Research Article
  • Citations45

GraphHop: An Enhanced Label Propagation Method for Node Classification.

  • Nov 01, 2023
  • IEEE Transactions on Neural Networks and Learning Systems
  • Tian Xie +2
  • Research Article
  • Citations5

Neighborhood Pattern Is Crucial for Graph Convolutional Networks Performing Node Classification.

  • Jun 01, 2024
  • IEEE transactions on neural networks and learning systems
  • Gongpei Zhao +5
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.