GeniePath: Graph Neural Networks with Adaptive Receptive Paths

We present, GeniePath, a scalable approach for learning adaptive receptive fields of neural networks defined on permutation invariant graph data. In GeniePath, we propose an adaptive path layer consists of two functions designed for breadth and depth exploration respectively, where the former learns the importance of different sized neighborhoods, while the latter extracts and filters signals aggregated from neighbors of different hops away. Our method works both in transductive and inductive settings, and extensive experiments compared with state-of-the-art methods show that our approaches are useful especially on large graph.