Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering

In this work, we are interested in generalizing convolutional neural networks (CNNs) from low-dimensional regular grids, where image, video and speech are represented, to high-dimensional irregular domains, such as social networks, brain connectomes or words' embedding, represented by graphs. We present a formulation of CNNs in the context of spectral graph theory, which provides the necessary mathematical background and efficient numerical schemes to design fast localized convolutional filters on graphs. Importantly, the proposed technique offers the same linear computational complexity and constant learning complexity as classical CNNs, while being universal to any graph structure. Experiments on MNIST and 20NEWS demonstrate the ability of this novel deep learning system to learn local, stationary, and compositional features on graphs.


Presented at:
Advances in Neural Information Processing Systems 29, Barcelona, Spain, December 5-10, 2016
Year:
2016
Keywords:
Laboratories:




 Record created 2016-07-01, last modified 2018-03-17

External links:
Download fulltextURL
Download fulltextURL
Download fulltextURL
Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)