Classifying Signals on Irregular Domains via Convolutional Cluster Pooling
This work addresses the challenge of applying neural models to irregular and complex domains, such as graph-structured data, for researchers and practitioners in machine learning.
The paper tackles the problem of classifying signals on irregular domains by introducing a Convolutional Cluster Pooling layer that generalizes CNNs to graph-structured data, achieving effectiveness in capturing local and global patterns across datasets like NTU RGB+D, CIFAR-10, and 20NEWS.
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.