Revisiting heterophily for graph neural networks
Abstract Graph Neural Networks (GNNs) extend basic Neural Networks (NNs) by using
graph structures based on the relational inductive bias (homophily assumption). While …
graph structures based on the relational inductive bias (homophily assumption). While …
When do graph neural networks help with node classification? investigating the homophily principle on node distinguishability
Homophily principle, ie, nodes with the same labels are more likely to be connected, has
been believed to be the main reason for the performance superiority of Graph Neural …
been believed to be the main reason for the performance superiority of Graph Neural …
Is heterophily a real nightmare for graph neural networks to do node classification?
Graph Neural Networks (GNNs) extend basic Neural Networks (NNs) by using the graph
structures based on the relational inductive bias (homophily assumption). Though GNNs are …
structures based on the relational inductive bias (homophily assumption). Though GNNs are …
[HTML][HTML] Data analytics on graphs part III: Machine learning on graphs, from graph topology to applications
Modern data analytics applications on graphs often operate on domains where graph
topology is not known a priori, and hence its determination becomes part of the problem …
topology is not known a priori, and hence its determination becomes part of the problem …
Introduction to graph signal processing
Graph signal processing deals with signals whose domain, defined by a graph, is irregular.
An overview of basic graph forms and definitions is presented first. Spectral analysis of …
An overview of basic graph forms and definitions is presented first. Spectral analysis of …
Complete the missing half: Augmenting aggregation filtering with diversification for graph convolutional networks
The core operation of current Graph Neural Networks (GNNs) is the aggregation enabled by
the graph Laplacian or message passing, which filters the neighborhood node information …
the graph Laplacian or message passing, which filters the neighborhood node information …
[HTML][HTML] Data analytics on graphs Part I: Graphs and spectra on graphs
Abstract The area of Data Analytics on graphs promises a paradigm shift, as we approach
information processing of new classes of data which are typically acquired on irregular but …
information processing of new classes of data which are typically acquired on irregular but …
Graph signal processing--Part I: Graphs, graph spectra, and spectral clustering
The area of Data Analytics on graphs promises a paradigm shift as we approach information
processing of classes of data, which are typically acquired on irregular but structured …
processing of classes of data, which are typically acquired on irregular but structured …
Graph signal processing--Part II: Processing and analyzing signals on graphs
The focus of Part I of this monograph has been on both the fundamental properties, graph
topologies, and spectral representations of graphs. Part II embarks on these concepts to …
topologies, and spectral representations of graphs. Part II embarks on these concepts to …
Contrastive learning under heterophily
W Yang, B Mirzasoleiman - arXiv preprint arXiv:2303.06344, 2023 - arxiv.org
Graph Neural Networks are powerful tools for learning node representations when task-
specific node labels are available. However, obtaining labels for graphs is expensive in …
specific node labels are available. However, obtaining labels for graphs is expensive in …