- Abstract: Graph convolution networks (GCN) have emerged as a leading method to classify nodes and graphs. These GCN have been combined with active learning (AL) methods, when a small chosen set of tagged examples can be used. Most AL-GCN use the sample class uncertainty as selection criteria, and not the graph. In contrast, representative sampling uses the graph, but not the prediction. We propose to combine the two and query nodes based on the uncertainty of the graph around them. We here propose two novel methods to select optimal nodes in AL-GCN that explicitly use the graph information to query for optimal nodes. The first method named regional uncertainty is an extension of the classical entropy measure, but instead of sampling nodes with high entropy, we propose to sample nodes surrounded by nodes of different classes, or nodes with high ambiguity. The second method called Adaptive Page-Rank is an extension of the page-rank algorithm, where nodes that have a low probability of being reached by random walks from tagged nodes are selected. We show that the latter is optimal when the fraction of tagged nodes is low, and when this fraction grows to one over the average degree, the regional uncertainty performs better than all existing methods. While we have tested these methods on graphs, such methods can be extended to any classification problem, where a distance can be defined between the input samples.
- Code: https://github.com/anonymous8375/Active-Learning-GCN
- Keywords: Active Learning, Graph Convolution Networks, Graph, Graph Topology
- TL;DR: Graph-oriented approaches to Active Learning for node classification