Maximal Independent Vertex Set applied to Graph Pooling

Stevan Stanovic (1, 2, 3) , Benoit Gaüzère (4, 5, 6, 7) , Luc Brun (1, 2, 3)

1 ENSICAEN - École Nationale Supérieure d'Ingénieurs de Caen
2 UNICAEN - Université de Caen Normandie
3 Equipe Image - Laboratoire GREYC - UMR6072
4 INSA Rouen Normandie - Institut national des sciences appliquées Rouen Normandie
5 UNIROUEN - Université de Rouen Normandie
6 ULH - Université Le Havre Normandie
7 LITIS - Laboratoire d'Informatique, du Traitement de l'Information et des Systèmes

Convolutional neural networks (CNN) have enabled major advances in image classification through convolution and pooling. In particular, image pooling transforms a connected discrete grid into a reduced grid with the same connectivity and allows reduction functions to take into account all the pixels of an image. However, a pooling satisfying such properties does not exist for graphs. Indeed, some methods are based on a vertex selection step which induces an important loss of information. Other methods learn a fuzzy clustering of vertex sets which induces almost complete reduced graphs. We propose to overcome both problems using a new pooling method, named MIVSPool. This method is based on a selection of vertices called surviving vertices using a Maximal Independent Vertex Set (MIVS) and an assignment of the remaining vertices to the survivors. Consequently, our method does not discard any vertex information nor artificially increase the density of the graph. Experimental results show an increase in accuracy for graph classification on various standard datasets.

Mots clés: Graph Neural Networks; Graph Pooling; Graph Classification; Maximal Independant Vertex Set

Domaines: Machine Learning [stat.ML]; Intelligence artificielle [cs.AI]; Vision par ordinateur et reconnaissance de formes [cs.CV]

Stevan Stanovic, Benoit Gaüzère, Luc Brun. Maximal Independent Vertex Set applied to Graph Pooling. Structural and Syntactic Pattern Recognition (SSPR), Aug 2022, Montréal, Canada. ⟨hal-03739114⟩