<ul><li>The problem of predicting node properties in graphs has gained attention for its applications.</li><li>Temporal graph neural networks (TGNNs) have been developed to handle dynamic node properties.</li><li>SPLASH is a simple yet powerful method proposed to predict node properties on edge streams under distribution shifts.</li><li>SPLASH improves the effectiveness of TGNNs with feature augmentation methods and an automatic feature selection method.</li></ul>

Simple yet Effective Node Property Prediction on Edge Streams under Distribution Shifts

Discover more