Graphs represent interconnected structures prevalent in a myriad of real-world scenarios.
Effective graph analytics, such as graph learning methods, enables users to gain profound …

Graph Neural Networks (GNNs) have been increasingly deployed in a plethora of
applications. However, the graph data used for training may contain sensitive personal …

Few-shot node classification is tasked to provide accurate predictions for nodes from novel
classes with only few representative labeled nodes. This problem has drawn tremendous …

Few-shot node classification, which aims to predict labels for nodes on graphs with only
limited labeled nodes as references, is of great significance in real-world graph mining …

Graph‐structured data, ranging from social networks to financial transaction networks, from
citation networks to gene regulatory networks, have been widely used for modeling a myriad …

Graph neural networks (GNNs) based on message passing have achieved remarkable
performance in graph machine learning. By combining it with the power of pseudo labeling …

Considering the extreme class imbalance in real-world graphs, increasing attention has
been paid to Few-Shot Node Classification (FSNC). However, existing methods in traditional …

Graph self-training (GST), which selects and assigns pseudo-labels to unlabeled nodes, is
popular for tackling label sparsity in graphs. However, recent study on homophily graphs …

To deal with distribution shifts in graph data, various graph out-of-distribution (OOD)
generalization techniques have been recently proposed. These methods often employ a two …

Inspired by the success of prompt in natural language processing, the graph prompt-based
methods are proposed to solve the classification tasks under the conditions with limited …