Label-GCN: An Effective Method for Adding Label Propagation to Graph Convolutional Networks

2021/04/05 by Claudio Bellei, Bellei, Claudio, Hussain Alattas +3 · 1 citation
Computer Science · #Advanced Graph Neural Networks #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and Data Classification #Text and Document Classification Technologies

paper · pdf · doi:10.48550/arxiv.2104.02153

openalex publication_date 2021/04/05 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We show that a modification of the first layer of a Graph Convolutional Network (GCN) can be used to effectively propagate label information across neighbor nodes, for binary and multi-class classification problems. This is done by selectively eliminating self-loops for the label features during the training phase of a GCN. The GCN architecture is otherwise unchanged, without any extra hyper-parameters, and can be used in both a transductive and inductive setting. We show through several experiments that, depending on how many labels are available during the inference phase, this strategy can lead to a substantial improvement in the model performance compared to a standard GCN approach, including with imbalanced datasets.

Citations

• Semi-Supervised Classification with Graph Convolutional Networks
• Inductive Representation Learning on Large Graphs
• Pitfalls of Graph Neural Network Evaluation
• Graph Neural Networks: A Review of Methods and Applications
• Simplifying Graph Convolutional Networks
• FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling
• Detecting Functionality-Specific Vulnerabilities via Retrieving Individual Functionality-Equivalent APIs in Open-Source Repositories
• Unifying Graph Convolutional Neural Networks and Label Propagation
• A Graph Convolutional Network Composition Framework for Semi-supervised\n Classification
• On the Equivalence of Decoupled Graph Convolution Network and Label Propagation
• Targeted Branching for the Maximum Independent Set Problem Using Graph Neural Networks

Cited by

• Neighbor-Sampling Based Momentum Stochastic Methods for Training Graph Neural Networks

Related

• Enhancing the Influence of Labels on Unlabeled Nodes in Graph Convolutional Networks
• Label-Aware Graph Convolutional Networks
• On the Equivalence of Decoupled Graph Convolution Network and Label Propagation
• Unifying Graph Convolutional Neural Networks and Label Propagation
• Expanding Label Sets for Graph Convolutional Networks