End-To-End Graph-based Deep Semi-Supervised Learning
This addresses the limitation of existing methods that only partially update graph factors, offering a more comprehensive solution for graph-based semi-supervised learning tasks.
The paper tackles the problem of graph quality in semi-supervised learning by proposing an end-to-end approach that dynamically optimizes all three graph factors (nodes, edges, and similarity measure) simultaneously, achieving improved performance on benchmark datasets.
The quality of a graph is determined jointly by three key factors of the graph: nodes, edges and similarity measure (or edge weights), and is very crucial to the success of graph-based semi-supervised learning (SSL) approaches. Recently, dynamic graph, which means part/all its factors are dynamically updated during the training process, has demonstrated to be promising for graph-based semi-supervised learning. However, existing approaches only update part of the three factors and keep the rest manually specified during the learning stage. In this paper, we propose a novel graph-based semi-supervised learning approach to optimize all three factors simultaneously in an end-to-end learning fashion. To this end, we concatenate two neural networks (feature network and similarity network) together to learn the categorical label and semantic similarity, respectively, and train the networks to minimize a unified SSL objective function. We also introduce an extended graph Laplacian regularization term to increase training efficiency. Extensive experiments on several benchmark datasets demonstrate the effectiveness of our approach.