Deeper Insights Into Graph Convolutional Networks for Semi-Supervised Learning

Counts differ because each database indexes a different set of publications. We treat OpenAlex as the canonical count; Google Scholar is not shown (no API, and crawling it violates its ToS).

Many interesting problems in machine learning are being revisited with new deep learning tools. For graph-based semi-supervised learning, a recent important development is graph convolutional networks (GCNs), which nicely integrate local vertex features and graph topology in the convolutional layers. Although the GCN model compares favorably with other state-of-the-art methods, its mechanisms are not clear and it still requires considerable amount of labeled data for validation and model selection. In this paper, we develop deeper insights into the GCN model and address its fundamental limits. First, we show that the graph convolution of the GCN model is actually a special form of Laplacian smoothing, which is the key reason why GCNs work, but it also brings potential concerns of over-smoothing with many convolutional layers. Second, to overcome the limits of the GCN model with shallow architectures, we propose both co-training and self-training approaches to train GCNs. Our approaches significantly improve GCNs in learning with very few labels, and exempt them from requiring additional labels for validation. Extensive experiments on benchmarks have verified our theory and proposals.

Last synced 2026-08-22 14:19 UTC

• Analyzing and Mitigating Asymmetric Learning for Product Cold-Start in E-Commerce Purchase Prediction with Graph Neural Networks: Similarity-Driven History Augmentation

  Journal of theoretical and applied electronic commerce research 2026 · 0 citations

• Structural Embedding Representation Method (SERM): A Masked Self-Supervised Framework for Structural Embedding Learning in Complex Networks

  Mathematics 2026 · 0 citations

• An interpretable graph neural network inspired by graph signal processing for mechanical fault diagnosis

  Structural Health Monitoring 2026 · 0 citations

• Beyond Graph Diameter: Structural Determinants of Long-Range Information Propagation in Message-Passing Neural Networks

  Mathematics 2026 · 0 citations