A Re-node Self-training Approach for Deep Graph-based Semi-supervised Classification on Multi-view Image Data

TL;DR

This paper introduces RSGSLM, a novel graph-based semi-supervised learning method that effectively integrates multi-view image data, pseudo-labeling, and topological correction within a GCN framework to improve classification accuracy.

Contribution

The paper proposes a new Re-node Self-training approach that combines feature transformation, multi-view graph fusion, and dynamic pseudo-label incorporation in GCNs for multi-view image classification.

Findings

RSGSLM outperforms existing semi-supervised methods on benchmark datasets.

The method effectively corrects topological imbalances near class boundaries.

Incorporating an unsupervised smoothing loss enhances model robustness.

Abstract

Recently, graph-based semi-supervised learning and pseudo-labeling have gained attention due to their effectiveness in reducing the need for extensive data annotations. Pseudo-labeling uses predictions from unlabeled data to improve model training, while graph-based methods are characterized by processing data represented as graphs. However, the lack of clear graph structures in images combined with the complexity of multi-view data limits the efficiency of traditional and existing techniques. Moreover, the integration of graph structures in multi-view data is still a challenge. In this paper, we propose Re-node Self-taught Graph-based Semi-supervised Learning for Multi-view Data (RSGSLM). Our method addresses these challenges by (i) combining linear feature transformation and multi-view graph fusion within a Graph Convolutional Network (GCN) framework, (ii) dynamically incorporating pseudo-labels into the GCN loss function to improve classification in multi-view data, and (iii) correcting topological imbalances by adjusting the weights of labeled samples near class boundaries. Additionally, (iv) we introduce an unsupervised smoothing loss applicable to all samples. This combination optimizes performance while maintaining computational efficiency. Experimental results on multi-view benchmark image datasets demonstrate that RSGSLM surpasses existing semi-supervised learning approaches in multi-view contexts.