Semi-Supervised Graph Learning Meets Dimensionality Reduction
This work addresses the problem of enhancing semi-supervised graph learning for researchers and practitioners by exploring classical dimensionality reduction, but it is incremental as it applies existing methods to new data contexts.
The paper investigates how dimensionality reduction techniques like PCA, t-SNE, and UMAP affect the performance of graph neural networks in semi-supervised node label propagation, finding that under certain conditions, these techniques can improve both label propagation and node clustering on benchmark datasets such as Cora and Citeseer.
Semi-supervised learning (SSL) has recently received increased attention from machine learning researchers. By enabling effective propagation of known labels in graph-based deep learning (GDL) algorithms, SSL is poised to become an increasingly used technique in GDL in the coming years. However, there are currently few explorations in the graph-based SSL literature on exploiting classical dimensionality reduction techniques for improved label propagation. In this work, we investigate the use of dimensionality reduction techniques such as PCA, t-SNE, and UMAP to see their effect on the performance of graph neural networks (GNNs) designed for semi-supervised propagation of node labels. Our study makes use of benchmark semi-supervised GDL datasets such as the Cora and Citeseer datasets to allow meaningful comparisons of the representations learned by each algorithm when paired with a dimensionality reduction technique. Our comprehensive benchmarks and clustering visualizations quantitatively and qualitatively demonstrate that, under certain conditions, employing a priori and a posteriori dimensionality reduction to GNN inputs and outputs, respectively, can simultaneously improve the effectiveness of semi-supervised node label propagation and node clustering. Our source code is freely available on GitHub.