Superior performance and ease of implementation have fostered the adoption of Convolutional Neural Networks (CNN s) for a wide array of inference and reconstruction tasks. CNNs implement three basic blocks: convolution, pooling and pointwise nonlinearity. Since the two first operations are well-defined only on regular-structured data such as audio or images, application of CNN s to contemporary datasets where the information is defined in irregular domains is challenging. This paper investigates CNNs architectures to operate on signals whose support can be modeled using a graph. Architectures that replace the regular convolution with a so-called linear shift-invariant graph filter have been recently proposed. This paper goes one step further and, under the framework of multiple-input multiple-output (MIMO) graph filters, imposes additional structure on the adopted graph filters, to obtain three new (more parsimonious) architectures. The proposed architectures result in a lower number of model parameters, reducing the computational complexity, facilitating the training, and mitigating the risk of overfitting. Simulations show that the proposed simpler architectures achieve similar performance as more complex models.
|Title of host publication||2018 IEEE 19th International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2018|
|Place of Publication||Piscataway, NJ|
|Number of pages||5|
|Publication status||Published - 2018|
|Event||SPAWC 2018: 19th IEEE International Workshop on Signal Processing Advances in Wireless Communications - Kalamata, Greece|
Duration: 25 Jun 2018 → 28 Jun 2018
Conference number: 19
|Period||25/06/18 → 28/06/18|
Bibliographical noteGreen Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care
Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.
- Convolutional neural networks
- graph signal processing
- network data