Graph data are inherently complex and heterogeneous, leading to a high natural diversity of
distributional shifts. However, it remains unclear how to build machine learning architectures …

Distribution shifts on graphs--the discrepancies in data distribution between training and
employing a graph machine learning model--are ubiquitous and often unavoidable in real …

Data augmentation has been widely used across various research domains in recent years.
However, data augmentation applied to real-world graph-structured data tends to suffer from …

Graph Neural Networks (GNNs) have achieved great success in semi-supervised node
classification. These methods usually assume the closed-set setting and classify unlabeled …

This thesis presents a new metric named Graph Distributional Analytics (GDA). This
approach uses Weisfeiler-Leman kernels, cosine similarity, and traditional statistical metrics …

The out-of-distribution (OOD) generalization challenge is a longstanding problem in graph
learning. Through studying the fundamental cause of data distribution shift, ie, the changes …

Abstract Graph Neural Networks are widely deployed in vast fields, but they often struggle to
maintain accurate representations as graphs evolve. We theoretically establish a lower …