Graph Mining under Data scarcity

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Rakaraddi, Appan, Siew-Kei, Lam, Pratama, Mahardhika, de Carvalho, Marcus
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917233549115392
author Rakaraddi, Appan
Siew-Kei, Lam
Pratama, Mahardhika
de Carvalho, Marcus
author_facet Rakaraddi, Appan
Siew-Kei, Lam
Pratama, Mahardhika
de Carvalho, Marcus
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2406_04825
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Graph Mining under Data scarcity
Rakaraddi, Appan
Siew-Kei, Lam
Pratama, Mahardhika
de Carvalho, Marcus
Machine Learning
Artificial Intelligence
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.
title Graph Mining under Data scarcity
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2406.04825