SMARTQUERY: An Active Learning Framework for Graph Neural Networks through Hybrid Uncertainty Reduction

TL;DR

SMARTQUERY is a novel active learning framework for graph neural networks that efficiently reduces uncertainty and achieves high performance with very few labeled nodes, leveraging hybrid uncertainty reduction and label propagation.

Contribution

It introduces a multi-stage active graph learning framework with hybrid uncertainty reduction and label propagation, enabling effective GNN training with minimal labeled data.

Findings

Outperforms state-of-the-art methods with up to 5 labeled nodes per class

Demonstrates strong performance across three network datasets

Efficiently exploits explicit and implicit graph information

Abstract

Graph neural networks have achieved significant success in representation learning. However, the performance gains come at a cost; acquiring comprehensive labeled data for training can be prohibitively expensive. Active learning mitigates this issue by searching the unexplored data space and prioritizing the selection of data to maximize model's performance gain. In this paper, we propose a novel method SMARTQUERY, a framework to learn a graph neural network with very few labeled nodes using a hybrid uncertainty reduction function. This is achieved using two key steps: (a) design a multi-stage active graph learning framework by exploiting diverse explicit graph information and (b) introduce label propagation to efficiently exploit known labels to assess the implicit embedding information. Using a comprehensive set of experiments on three network datasets, we demonstrate the competitive performance of our method against state-of-the-arts on very few labeled data (up to 5 labeled nodes per class).