Active Learning for Graph Neural Networks via Node Feature Propagation
This addresses the label-sparse issue in graph-based machine learning, which is a domain-specific incremental advancement.
The paper tackles the problem of label scarcity in Graph Neural Networks (GNNs) for node classification by proposing an active learning method using node feature propagation and K-Medoids clustering, achieving consistent and significant performance improvements over baselines on four benchmark datasets.
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.