Regional based query in graph active learning

TL;DR

This paper introduces regional-based query strategies for graph active learning, leveraging neighbor class uncertainty and PageRank extensions to improve node classification accuracy with minimal labeled data.

Contribution

It proposes two novel regional uncertainty criteria for active learning in graph neural networks, outperforming existing methods especially with low labeled node fractions.

Findings

PageRank-based criterion is optimal at low labeled node fractions.

Regional uncertainty surpasses existing methods as labeled fraction approaches one.

Methods can be extended to other classification problems with defined distance metrics.

Abstract

Graph convolution networks (GCN) have emerged as the leading method to classify node classes in networks, and have reached the highest accuracy in multiple node classification tasks. In the absence of available tagged samples, active learning methods have been developed to obtain the highest accuracy using the minimal number of queries to an oracle. The current best active learning methods use the sample class uncertainty as selection criteria. However, in graph based classification, the class of each node is often related to the class of its neighbors. As such, the uncertainty in the class of a node's neighbor may be a more appropriate selection criterion. We here propose two such criteria, one extending the classical uncertainty measure, and the other extending the page-rank algorithm. 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 this methods on graphs, such methods can be extended to any classification problem, where a distance metrics can be defined between the input samples. All the code used can be accessed at : https://github.com/louzounlab/graph-al All the datasets used can be accessed at : https://github.com/louzounlab/DataSets