Active Learning for Graph Neural Networks via Node Feature Propagation

TL;DR

This paper introduces a novel active learning method for graph neural networks that uses node feature propagation and clustering to select informative nodes, improving label efficiency in node classification tasks.

Contribution

It proposes a new active learning approach for GNNs combining feature propagation and clustering, with theoretical analysis and superior experimental performance.

Findings

Outperforms baseline methods on four benchmark datasets

Significantly reduces the number of labeled nodes needed

Provides theoretical justification for the method's effectiveness

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.