Real-world graphs naturally exhibit hierarchical or cyclical structures ...
Pretraining molecular representations from large unlabeled data is essen...
Since the recent advent of regulations for data protection (e.g., the Ge...
To overcome the quadratic cost of self-attention, recent works have prop...
Despite the evolution of Convolutional Neural Networks (CNNs), their
per...
Graph pooling is a crucial operation for encoding hierarchical structure...
Many problems in computer vision and machine learning can be cast as lea...
We show that standard Transformers without graph-specific modifications ...
Across many data domains, co-occurrence statistics about the joint appea...