Recent years have witnessed fast developments of graph neural networks (GNNs) that have
benefited myriads of graph analytic tasks and applications. In general, most GNNs depend …

Abstract Graph Neural Networks (GNNs) extend basic Neural Networks (NNs) by using
graph structures based on the relational inductive bias (homophily assumption). While …

We investigate graph neural networks on graphs with heterophily. Some existing methods
amplify a node's neighborhood with multi-hop neighbors to include more nodes with …

Many widely used datasets for graph machine learning tasks have generally been
homophilous, where nodes with similar labels connect to each other. Recently, new Graph …

We investigate the representation power of graph neural networks in the semi-supervised
node classification task under heterophily or low homophily, ie, in networks where …

Graph neural networks (GNNs) have shown great prowess in learning representations
suitable for numerous graph-based machine learning tasks. When applied to semi …

Node classification is a classical graph representation learning task on which Graph Neural
Networks (GNNs) have recently achieved strong results. However, it is often believed that …

In node classification tasks, graph convolutional neural networks (GCNs) have
demonstrated competitive performance over traditional methods on diverse graph data …

Homophily principle,\ie {} nodes with the same labels or similar attributes are more likely to
be connected, has been commonly believed to be the main reason for the superiority of …

Abstract Recent studies on Graph Neural Networks (GNNs) provide both empirical and
theoretical evidence supporting their effectiveness in capturing structural patterns on both …