Training deep graph neural networks (GNNs) is notoriously hard. Besides the standard
plights in training deep architectures such as vanishing gradients and overfitting, it also …

Despite the recent success of graph neural networks (GNN), common architectures often
exhibit significant limitations, including sensitivity to oversmoothing, long-range …

Heterogeneous graph neural networks (GNNs) achieve strong performance on node
classification tasks in a semi-supervised learning setting. However, as in the simpler …

The study of graph neural networks has revealed that they can unleash new applications in
a variety of disciplines using such a basic process that we cannot imagine in the context of …

Deep learning models such as the Transformer are often constructed by heuristics and
experience. To provide a complementary foundation, in this work we study the following …

Hypergraphs are a powerful abstraction for representing higher-order interactions between
entities of interest. To exploit these relationships in making downstream predictions, a …

Among the many variants of graph neural network (GNN) architectures capable of modeling
data with cross-instance relations, an important subclass involves layers designed such that …

It has been observed that graph neural networks (GNN) sometimes struggle to maintain a
healthy balance between the efficient modeling long-range dependencies across nodes …

For supervised learning with tabular data, decision tree ensembles produced via boosting
techniques generally dominate real-world applications involving iid training/test sets …

Graph neural networks (GNNs) for link prediction can loosely be divided into two broad
categories. First, node-wise architectures pre-compute individual embeddings for each node …