Diffusion models have emerged as a powerful new family of deep generative models with
record-breaking performance in many applications, including image synthesis, video …

Artificial General Intelligence (AGI) has revolutionized numerous fields, yet its integration
with graph data, a cornerstone in our interconnected world, remains nascent. This paper …

Graph contrastive learning (GCL) has emerged as a dominant technique for graph
representation learning which maximizes the mutual information between paired graph …

Deep learning on graphs has attracted significant interests recently. However, most of the
works have focused on (semi-) supervised learning, resulting in shortcomings including …

Enabling effective and efficient machine learning (ML) over large-scale graph data (eg,
graphs with billions of edges) can have a great impact on both industrial and scientific …

Various graph contrastive learning models have been proposed to improve the performance
of tasks on graph datasets in recent years. While effective and prevalent, these models are …

Deep learning on graphs has recently achieved remarkable success on a variety of tasks,
while such success relies heavily on the massive and carefully labeled data. However …

Inspired by the recent success of self-supervised methods applied on images, self-
supervised learning on graph structured data has seen rapid growth especially centered on …

We introduce a conceptually simple yet effective model for self-supervised representation
learning with graph data. It follows the previous methods that generate two views of an input …

Graph contrastive learning (GCL) alleviates the heavy reliance on label information for
graph representation learning (GRL) via self-supervised learning schemes. The core idea is …