Classifying Signals on Irregular Domains via Convolutional Cluster Pooling

TL;DR

This paper introduces a hierarchical convolutional clustering method for classifying signals on irregular graph domains, extending CNN principles to complex, non-Euclidean data structures.

Contribution

It proposes a Convolutional Cluster Pooling layer that captures multi-scale local regions on graphs, generalizing CNNs to irregular domains.

Findings

Effective in capturing local and global patterns

Demonstrated on diverse datasets like NTU RGB+D, CIFAR-10, 20NEWS

Outperforms existing methods in graph signal classification

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.