To accommodate such an asymmetric structure of directed graphs, we propose a simple yet remarkably effective SSL framework for directed graph analysis to ...

We propose a simple yet remarkably effective SSL framework for directed graph analysis to incorporate such one-way information passing.

We first design asymmetric graph reconstruction as a self- supervised auxiliary task for directed graphs. We then develop a directed graph neural network with ...

Asymmetric Self-Supervised Graph Neural Networks · List of references · Publications that cite this publication.

In graph data analysis, SSL can potentially be of great importance to make use of a massive amount of unlabeled graphs such as molecular graphs [21, 22]. With ...

Graph data augmentations can provide a promising method to expand labeled samples cheaply. However, graph data augmentations will damage the capacity of GNNs to ...

Graph Neural Networks (GNNs) have demonstrated great power for the semi-supervised node classification task. However, most GNN methods are sensitive to the ...

Experimental results show that the simple GraphACL significantly outperforms state-of-the-art graph contrastive learning and self-supervised learning methods on ...

We introduce a conceptually simple yet effective model for self-supervised representation learning with graph data. It follows the previous methods that ...

Self-supervised learning (SSL): spontaneously find supervised signals from the data itself by constructing pretext tasks. ➢ Self-supervised learning has ...