Y Yan, M Hashemi, K Swersky, Y Yang… - 2022 IEEE International …, 2022 - par.nsf.gov
In node classification tasks, graph convolutional neural networks (GCNs) have demonstrated competitive performance over traditional methods on diverse graph data …
Y Yan, M Hashemi, K Swersky, Y Yang, D Koutra - researchgate.net
In node classification tasks, graph convolutional neural networks (GCNs) have demonstrated competitive performance over traditional methods on diverse graph data …
Y Yan, M Hashemi, K Swersky, Y Yang… - 2022 IEEE International …, 2022 - computer.org
In node classification tasks, graph convolutional neural networks (GCNs) have demonstrated competitive performance over traditional methods on diverse graph data …
Y Yan, M Hashemi, K Swersky, Y Yang… - arXiv preprint arXiv …, 2021 - arxiv.org
In node classification tasks, graph convolutional neural networks (GCNs) have demonstrated competitive performance over traditional methods on diverse graph data …
Y Yan, M Hashemi, K Swersky, Y Yang… - arXiv e …, 2021 - ui.adsabs.harvard.edu
In node classification tasks, graph convolutional neural networks (GCNs) have demonstrated competitive performance over traditional methods on diverse graph data …
Y Yan, M Hashemi, K Swersky, Y Yang, D Koutra - openreview.net
In node classification tasks, heterophily and oversmoothing are two problems that can hurt the performance of graph convolutional neural networks (GCNs). The heterophily problem …
Y Yan, M Hashemi, K Swersky, Y Yang, D Koutra - researchgate.net
Most graph neural networks (GNN) perform poorly in graphs where neighbors typically have different features/classes (heterophily) and when stacking multiple layers (oversmoothing) …