DynamicGraphNeuralNetworksUnder Spatio-TemporalDistributionShift

Lastly, we propose an invariance regularization term to minimize the variance of predictions in intervened distributions so that our model can make predictions based on invariant patterns with stable predictive abilities and thereforehandle distribution shifts. Experiments onthree real-worlddatasets andone synthetic dataset demonstrate the superiority ofour method overstate-of-the-art baselines under distribution shifts.