A combinatorial approach to graphlet counting
By Tomaž Hočevar, Jaka Demsar. 2014
242 citations recorded by the source corpus.
Subfields: Computer Vision and Pattern Recognition, Molecular Biology, Statistical and Nonlinear Physics
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- William L. Hamilton
- Jure Leskovec
- Marinka Zitnik
- Xiang Ren
- Jiaxuan You
- Rex Ying
- Jaewon Yang
- Peter W. Battaglia
In Molecular Biology
- Jure Leskovec
- Rex Ying
- Marinka Zitnik
- William L. Hamilton
- Jiaxuan You
- Xiang Ren
- Petar Velickovic
- Stephan Günnemann
In Statistical and Nonlinear Physics
- William L. Hamilton
- Jure Leskovec
- Marinka Zitnik
- Rex Ying
- Jiaxuan You
- Xiang Ren
- Jaewon Yang
- Manuel Gomez-Rodriguez
Citations in the corpus
- GNNGuard: Defending Graph Neural Networks against Adversarial Attacks (2020, methodology): “The graphlet degree vectors are calculated using the orbit counting algorithm [54], are independent of node attributes, and provide a highly constraining measure of local graph topology.”
- GraphRNN: A Deep Generative Model for Graphs (2018, methodology): “In experiments, we show this derived MMD score for degree and clustering coefficient distributions, as well as average orbit counts statistics, i.e., the number of occurrences of all orbits with 4 nodes (to capture higher-level motifs) (Hočevar & Demšar, 2014).”
- Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting (2020, unknown): “[52], [53], [54], [55], [56], [57] provide practical implementa-”