Predict then Propagate: Combining neural networks with personalized pagerank for classification on graphs

171 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

PairNorm: Tackling Oversmoothing in GNNs (2019, background): “There exist a few other work addressing oversmoothing (Klicpera et al., 2019; Li et al., 2018; Rong et al., 2019; Xu et al., 2018) however they design specialized architectures and not simple “patch” procedures like PAIRNORM that can be applied on top of any GNN.”
Adversarial Attacks on Node Embeddings via Graph Poisoning (2018, unknown): “Moreover, while many semi-supervised learning methods (Defferrard et al., 2016; Kipf & Welling, 2017; Klicpera et al., 2019) have been introduced, we focus on unsupervised methods since they are often used in practice due to their flexibility in simultaneously solving various downstream tasks.”
On the Bottleneck of Graph Neural Networks and its Practical Implications (2020, background): “…The over-smoothing phenomenon is related, but not identical, to over-squashing: node representations become indistinguishable and prediction performance severely degrades when the number of layers increases (Li et al., 2018; Klicpera et al., 2019; Wu et al., 2020; Oono and Suzuki, 2020).”
Contrastive Multi-View Representation Learning on Graphs (2020, methodology): “…replaces adjacency matrix in graph convolution with a spar-siﬁed diffusion matrix (Klicpera et al., 2019b), whereas, late-fusion models (Tsitsulin et al., 2018; Klicpera et al., 2019a) project the node features into a latent space and then propagate the learned representation based on a diffusion.”