Classifying Signals on Irregular Domains via Convolutional Cluster Pooling

Abstract: We present a novel and hierarchical approach for supervised classification of signals spanning over a fixed graph, reflecting shared properties of the dataset. To this end, we introduce a Convolutional Cluster Pooling layer exploiting a multi-scale clustering in order to highlight, at different resolutions, locally connected regions on the input graph. Our proposal generalises well-established neural models such as Convolutional Neural Networks (CNNs) on irregular and complex domains, by means of the exploitation of the weight sharing property in a graph-oriented architecture. In this work, such property is based on the centrality of each vertex within its soft-assigned cluster. Extensive experiments on NTU RGB+D, CIFAR-10 and 20NEWS demonstrate the effectiveness of the proposed technique in capturing both local and global patterns in graph-structured data out of different domains.

Citation:

Porrello, Angelo; Abati, Davide; Calderara, Simone; Cucchiara, Rita "Classifying Signals on Irregular Domains via Convolutional Cluster Pooling" Volume 89: International Conference on Artificial Intelligence and Statistics (AISTATS) 2019, Naha,Okinawa, Japan., vol. 89, Naha, Okinawa, Japan, Tuesday, 16 April 2019, 2019

 not available

Paper download:

• Author version: