SMARTQUERY: An Active Learning Framework for Graph Neural Networks through Hybrid Uncertainty Reduction
This addresses the data labeling cost issue for researchers and practitioners using graph neural networks, but it is incremental as it builds on existing active learning methods.
The paper tackles the problem of expensive labeled data acquisition for graph neural networks by proposing SMARTQUERY, an active learning framework that uses a hybrid uncertainty reduction function to train with very few labeled nodes, achieving competitive performance with up to 5 labeled nodes per class.
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).