Personalized Embedding Propagation: Combining Neural Networks on Graphs with Personalized PageRank

By Johannes Klicpera, Aleksandar Bojchevski, Stephan Günnemann. 2018

61 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.

1. Haopeng Zhang
2. Péter Mernyei
3. Jiawei Zhang
4. Li Sun
5. Cătălina Cangea
6. Congying Xia
7. Hongkuan Zhou
8. Viktor K. Prasanna

Citations in the corpus

• Graph-Bert: Only Attention is Needed for Learning Graph Representations (2020, background): “…proposed by present include GCN [Kipf and Welling, 2016], GraphSAGE [Hamilton et al., 2017] and LOOPYNET [Zhang et al., 2018], based on which various extended models, e.g., GAT [Veličković et al., 2018], and other variants [Sun et al., 2019; Klicpera et al., 2018], have been introduced as well.”
• Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networks (2020, methodology): “Three GNN models were evaluated: GCN (Kipf & Welling, 2016a), GAT (Veliˇckovi´c et al., 2017) and APPNP (Klicpera et al., 2018).”
• GraphSAINT: Graph Sampling Based Inductive Learning Method (2019, methodology): “Klicpera et al. (2018) combines PageRank with GCNs to enable efficient information propagation from many hops away.”