Training Graph Neural Networks (GNNs) on large graphs is a fundamental challenge due to
the high memory usage, which is mainly occupied by activations (eg, node embeddings) …

Given the importance of getting calibrated predictions and reliable uncertainty estimations,
various post-hoc calibration methods have been developed for neural networks on standard …

Sampling subgraphs for training Graph Neural Networks (GNNs) is receiving much attention
from the GNN community. While a variety of methods have been proposed, each method …

Abstract Graph Neural Networks (GNNs) are limited in their propagation operators. In many
cases, these operators often contain non-negative elements only and are shared across …

Increasing the depth of GCN, which is expected to permit more expressivity, is shown to
incur performance detriment especially on node classification. The main cause of this lies in …

Recent observations have advanced our understanding of the neural network optimization
landscape, revealing the existence of (1) paths of high accuracy containing diverse solutions …

Abstract We present Graph Neural Diffusion (GRAND) that approaches deep learning on
graphs as a continuous diffusion process and treats Graph Neural Networks (GNNs) as …

The emergence of evolving data privacy policies and regulations has sparked a growing
interest in the concept of" machine unlearning", which involves enabling machine learning …

Modern neural network architectures often generalize well despite containing many more
parameters than the size of the training dataset. This paper explores the generalization …

In the recent literature of Graph Neural Networks (GNN), the expressive power of models
has been studied through their capability to distinguish if two given graphs are isomorphic or …