Coupling Graph Neural Networks with Fractional Order Continuous Dynamics: A Robustness Study

arXiv:2401.04331v2 Announce Type: replace
Abstract: In this work, we rigorously investigate the robustness of graph neural fractional-order differential equation (FDE) models. This framework extends beyond traditional graph neural (integer-order) ordinary differential equation (ODE) models by implementing the time-fractional Caputo derivative. Utilizing fractional calculus allows our model to consider long-term memory during the feature updating process, diverging from the memoryless Markovian updates seen in traditional graph neural ODE models. The superiority of graph neural FDE models over graph neural ODE models …

abstract arxiv beyond calculus continuous cs.ai cs.lg differential differential equation dynamics equation framework graph graph neural networks networks neural networks ordinary robustness study type work