Continuous Graph Neural Networks

This paper builds the connection between graph neural networks and traditional dynamical systems. Existing graph neural networks essentially define a discrete dynamic on node representations with multiple graph convolution layers. We propose continuous graph neural networks (CGNN), which generalise existing graph neural networks into the continuous-time dynamic setting. 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 different 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 networks are robust to over-smoothing and hence capture the long-range dependencies between nodes. Experimental results on the task of node classification prove the effectiveness of our proposed approach over competitive baselines.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/31/2022

Continuous Temporal Graph Networks for Event-Based Graph Data

There has been an increasing interest in modeling continuous-time dynami...
research
02/13/2023

TIGER: Temporal Interaction Graph Embedding with Restarts

Temporal interaction graphs (TIGs), consisting of sequences of timestamp...
research
11/12/2022

Significant Ties Graph Neural Networks for Continuous-Time Temporal Networks Modeling

Temporal networks are suitable for modeling complex evolving systems. It...
research
06/09/2023

Intensity Profile Projection: A Framework for Continuous-Time Representation Learning for Dynamic Networks

We present a new algorithmic framework, Intensity Profile Projection, fo...
research
05/14/2023

Decoupled Graph Neural Networks for Large Dynamic Graphs

Real-world graphs, such as social networks, financial transactions, and ...
research
08/31/2023

Rank Collapse Causes Over-Smoothing and Over-Correlation in Graph Neural Networks

Our study reveals new theoretical insights into over-smoothing and featu...
research
08/14/2017

Situation Recognition with Graph Neural Networks

We address the problem of recognizing situations in images. Given an ima...

Please sign up or login with your details

Forgot password? Click here to reset