Graph Mining under Data scarcity

TL;DR

This paper introduces an Uncertainty Estimator framework that enhances GNN-based node classification in graphs with limited labeled data, improving accuracy without requiring specialized meta-learning architectures.

Contribution

It proposes a novel Uncertainty Estimator that can be integrated with any GNN backbone to boost few-shot node classification performance.

Findings

Outperforms baseline models on multiple datasets.

Improves classification accuracy in few-shot settings.

Works with various GNN architectures.

Abstract

Multitude of deep learning models have been proposed for node classification in graphs. However, they tend to perform poorly under labeled-data scarcity. Although Few-shot learning for graphs has been introduced to overcome this problem, the existing models are not easily adaptable for generic graph learning frameworks like Graph Neural Networks (GNNs). Our work proposes an Uncertainty Estimator framework that can be applied on top of any generic GNN backbone network (which are typically designed for supervised/semi-supervised node classification) to improve the node classification performance. A neural network is used to model the Uncertainty Estimator as a probability distribution rather than probabilistic discrete scalar values. We train these models under the classic episodic learning paradigm in the $n$-way, $k$-shot fashion, in an end-to-end setting. Our work demonstrates that implementation of the uncertainty estimator on a GNN backbone network improves the classification accuracy under Few-shot setting without any meta-learning specific architecture. We conduct experiments on multiple datasets under different Few-shot settings and different GNN-based backbone networks. Our method outperforms the baselines, which demonstrates the efficacy of the Uncertainty Estimator for Few-shot node classification on graphs with a GNN.