Classifying Signals on Irregular Domains via Convolutional Cluster Pooling
By Angelo Porrello, Davide Abati, Simone Calderara, Rita Cucchiara. 2019
11 citations recorded by the source corpus.
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.
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Angelo Porrello
- Simone Calderara
- Pietro Buzzega
- Stefano Vincenzi
- Alessio Monti
- Carla Ippoliti
- Annamaria Conte
- Rita Cucchiara
Citations in the corpus
- Spotting Insects from Satellites: Modeling the Presence of Culicoides Imicola Through Deep CNNs (2019, background): “Graph Convolutional Neural Networks (GCNNs) [29], [30] and propose a novel inference engine, which would exploit the local dynamics arising from the spread of C.”
- How many Observations are Enough? Knowledge Distillation for Trajectory Forecasting (2022, background): “Recent improvements in graph machine learning [21,25, 28, 43] motivated the adoption of such flexible structures to model agents relationships.”