Spectral Clustering with Graph Neural Networks for Graph Pooling

By Filippo Maria Bianchi, Daniele Grattarola, Cesare Alippi. International Conference on Machine Learning, 2019

551 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.

Utilizing graph machine learning within drug discovery and development (2021, background): “theory such as minimum cuts [100, 102] and maximal cliques [101] on which to base pooling.”
Machine Learning on Graphs: A Model and Comprehensive Taxonomy (2020, background): “Other work focuses on optimizing graph partitions (Bianchi et al., 2020; Tsitsulin et al., 2020b), finding assignments that aim to fulfill an objective (e.”
Graph Clustering with Graph Neural Networks (2020, methodology): “MinCut pooling [4] addresses this problem by adapting spectral orthogonality constraint in the form of softorthogonality [2] regularization C⊤C − I F .”