Temporal attributed network embedding aspires to learn a low-dimensional vector
representation for each node in each snapshot of a temporal network, which can be capable …

For graph self-supervised learning (GSSL), masked autoencoder (MAE) follows the
generative paradigm and learns to reconstruct masked graph edges or node features while …

Contrastive learning, a powerful self-supervised learning paradigm, has shown its efficacy in
learning embed dings from independent and identically distributed (IID) as well as non-IID …

Graph self-supervised learning aiming to learn the graph representation without much label
information is an important tasks in data mining and machine learning since labeled graph …

Deep Evidential Regression (DER) places a prior on the original Gaussian likelihood
function and treats learning as an evidence acquisition process to quantify uncertainty by …

Graph Neural Networks (GNNs) have emerged as an effective tool for graph classification,
yet their reliance on extensive labeled data poses a significant challenge, especially when …

The rich information underlying graphs has inspired further investigation of unsupervised
graph representation. Existing studies mainly depend on node features and topological …

Graph contrastive learning is a representative self-supervised graph learning that has
demonstrated excellent performance in learning node representations. Despite the …

Federated Graph Learning (FGL) enables multiple clients to jointly train powerful graph
learning models, eg, Graph Neural Networks (GNNs), without sharing their local graph data …

Graph Contrastive Learning frameworks have demonstrated success in generating high-
quality node representations. The existing research on efficient data augmentation methods …