Contrastive learning models have been pivotal in this transformation ... The image encoder leverages a vision transformer architecture with a masked autoencoder reconstruction loss, while the text ...

[paper] [code] [Fan2020] ANOMALYDAE: Dual Autoencoder for Anomaly Detection on ... [paper] [Zheng2021] Generative and Contrastive Self-Supervised Learning for Graph Anomaly Detection in TKDE, 2021.

Abstract: Unsupervised graph-structure learning (GSL) which aims to learn an effective ... To tackle the above issue, we present a multilevel contrastive graph masked autoencoder (MCGMAE) for ...

By employing a graph embedding variational autoencoder and incorporating a deep contrastive strategy, SpaCAE achieves a balance between spatial local information and global information of expression, ...

AE-GCN is an integrative scheme that incorporates the AE and GCN learning processes ... In this paper, AE-GCN combines the autoencoder and graph convolutional neural network to achieve effective ...