Learning with Multigraph Convolutional Filters
This work addresses the challenge of processing information on multigraphs, which is incremental as it extends convolutional methods to a more complex graph structure.
The authors tackled the problem of learning on multigraphs by introducing multigraph convolutional neural networks (MGNNs) based on algebraic signal processing, and they demonstrated performance improvements in an optimal resource allocation task for multi-channel communication systems.
In this paper, we introduce a convolutional architecture to perform learning when information is supported on multigraphs. Exploiting algebraic signal processing (ASP), we propose a convolutional signal processing model on multigraphs (MSP). Then, we introduce multigraph convolutional neural networks (MGNNs) as stacked and layered structures where information is processed according to an MSP model. We also develop a procedure for tractable computation of filter coefficients in the MGNN and a low cost method to reduce the dimensionality of the information transferred between layers. We conclude by comparing the performance of MGNNs against other learning architectures on an optimal resource allocation task for multi-channel communication systems.