Skip to yearly menu bar Skip to main content


Diffusion-Convolutional Neural Networks

James Atwood · Don Towsley

Area 5+6+7+8 #44

Keywords: [ Semi-Supervised Learning ] [ Structured Prediction ] [ Graph-based Learning ] [ Deep Learning or Neural Networks ]


We present diffusion-convolutional neural networks (DCNNs), a new model for graph-structured data. Through the introduction of a diffusion-convolution operation, we show how diffusion-based representations can be learned from graph-structured data and used as an effective basis for node classification. DCNNs have several attractive qualities, including a latent representation for graphical data that is invariant under isomorphism, as well as polynomial-time prediction and learning that can be represented as tensor operations and efficiently implemented on a GPU. Through several experiments with real structured datasets, we demonstrate that DCNNs are able to outperform probabilistic relational models and kernel-on-graph methods at relational node classification tasks.

Live content is unavailable. Log in and register to view live content