Active Learning for Graph Neural Networks via Node Feature Propagation

Abstract

Graph Neural Networks (GNNs) for prediction tasks like node classification or edge prediction have received increasing attention in recent machine learning from graphically structured data. However, a large quantity of labeled graphs is difficult to obtain, which significantly limits the true success of GNNs. Although active learning has been widely studied for addressing label-sparse issues with other data types like text, images, etc., how to make it effective over graphs is an open question for research. In this paper, we present an investigation on active learning with GNNs for node classification tasks. Specifically, we propose a new method, which uses node feature propagation followed by K-Medoids clustering of the nodes for instance selection in active learning. With a theoretical bound analysis we justify the design choice of our approach. In our experiments on four benchmark datasets, the proposed method outperforms other representative baseline methods consistently and significantly.

15 pages, 5 figures

References in corpus (9)

• Semi-Supervised Classification with Graph Convolutional Networks
• Simplifying Graph Convolutional Networks
• Representation Learning on Graphs with Jumping Knowledge Networks
• Junction Tree Variational Autoencoder for Molecular Graph Generation
• A Convergence Theory for Deep Learning via Over-Parameterization
• Active Learning for Graph Embedding
• A Meta-Learning Approach to One-Step Active Learning
• Near-Optimal Discrete Optimization for Experimental Design: A Regret Minimization Approach
• Importance Weighted Active Learning

Cited by in corpus (7)

• Graph Policy Network for Transferable Active Learning on Graphs
• Adversarial Model Extraction on Graph Neural Networks
• Sequential Graph Convolutional Network for Active Learning
• When Contrastive Learning Meets Active Learning: A Novel Graph Active Learning Paradigm with Self-Supervision
• A low discrepancy sequence on graphs
• Deep Active Learning by Model Interpretability
• Improving Neural Model Performance through Natural Language Feedback on Their Explanations