Real-world networks often consist of millions of heterogenous elements that interact at
multiple timescales and length scales. The fields of statistical physics and control theory both …

The stochastic block model (SBM) is a random graph model with planted clusters. It is widely
employed as a canonical model to study clustering and community detection, and provides …

This work develops mixup for graph data. Mixup has shown superiority in improving the
generalization and robustness of neural networks by interpolating features and labels …

Despite recent success in using the invariance principle for out-of-distribution (OOD)
generalization on Euclidean data (eg, images), studies on graph data are still limited …

Vector representations of graphs and relational structures, whether hand-crafted feature
vectors or learned representations, enable us to apply standard data analysis and machine …

As many readers may know, graph theory is a fundamental branch of mathematics that
explores networks made up of nodes and edges, focusing on their paths, structures, and …

In general, graph representation learning methods assume that the train and test data come
from the same distribution. In this work we consider an underexplored area of an otherwise …

Matrices of (approximate) low rank are pervasive in data science, appearing in movie
preferences, text documents, survey data, medical records, and genomics. While there is a …

Graph neural networks (GNNs) rely on graph convolutions to extract local features from
network data. These graph convolutions combine information from adjacent nodes using …

Numerous recent works have analyzed the expressive power of message-passing graph
neural networks (MPNNs), primarily utilizing combinatorial techniques such as the $1 …