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.
James Atwood (UMass Amherst)
Don Towsley (UMass Amherst)
More from the Same Authors
2021 Poster: Cooperative Stochastic Bandits with Asynchronous Agents and Constrained Feedback »
Lin Yang · Yu-Zhen Janice Chen · Stephen Pasteris · Mohammad Hajiesmaili · John C. S. Lui · Don Towsley