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.
|Task||Dataset||Model||Metric name||Metric value||Global rank||Compare|
|Node Classification||Citeseer||ChebNet||Accuracy||69.8%||# 7|
|Node Classification||Cora||ChebNet||Accuracy||81.2%||# 5|
|Node Classification||Pubmed||ChebNet||Accuracy||74.4%||# 8|