Timezone: »

Continuous Graph Neural Networks
Louis-Pascal Xhonneux · Meng Qu · Jian Tang

Thu Jul 16 06:00 AM -- 06:45 AM & Thu Jul 16 05:00 PM -- 05:45 PM (PDT) @

This paper builds on the connection between graph neural networks and traditional dynamical systems. We propose continuous graph neural networks (CGNN), which generalise existing graph neural networks with discrete dynamics in that they can be viewed as a specific discretisation scheme. The key idea is how to characterise the continuous dynamics of node representations, i.e. the derivatives of node representations, w.r.t. time.Inspired by existing diffusion-based methods on graphs (e.g. PageRank and epidemic models on social networks), we define the derivatives as a combination of the current node representations,the representations of neighbors, and the initial values of the nodes. We propose and analyse two possible dynamics on graphs—including each dimension of node representations (a.k.a. the feature channel) change independently or interact with each other—both with theoretical justification. The proposed continuous graph neural net-works are robust to over-smoothing and hence allow us to build deeper networks, which in turn are able to capture the long-range dependencies between nodes. Experimental results on the task of node classification demonstrate the effectiveness of our proposed approach over competitive baselines.

Author Information

Louis-Pascal Xhonneux (Mila / Université de Montréal)
Meng Qu (Mila)
Jian Tang (HEC Montreal & MILA)

More from the Same Authors