Improving Graph Variational Autoencoders with Multi-Hop Simple Convolutions

Abstract

Variational auto-encoding architectures represent one of the most popular approaches to graph generative modeling. These models comprise encoder and a decoder networks, which map back and forth between the input and latent spaces. Notably, most of the literature in variational autoencoders (VAEs) for graphs focuses on developing more efficient architectures at the expense of increased complexity. In this work, we pursue an orthogonal direction and leverage multi-hop linear graph convolutional layers to create efficient yet simple encoders, boosting the performance of graph autoencoders. Our results demonstrate that our approach outperforms popular graph VAE baselines in link prediction tasks.

Detecção de Intrusão em Sistemas IoT Baseada em Comitê de Classificadores

“…Nos últimos anos, os métodos baseados em aprendizado de máquina (ML -Machine Learning) ganharam grande destaque e consolidaram-se como as principais estratégias para detecc ¸ão de anomalias. Todavia, os modelos de aprendizado de máquina precisam ser treinados com grandes volumes de dados para alcanc ¸ar altas taxas de acurácia, precisão, recall e F1-score [do Nascimento et al 2021].…”