GeniePath

2000년 도입 · 논문 1편에서 사용

GeniePath is 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 complementary 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. Description and image from: GeniePath: Graph Neural Networks with Adaptive Receptive Paths

출처: GeniePath: Graph Neural Networks with Adaptive Receptive Paths

소개 논문: GeniePath: Graph Neural Networks with Adaptive Receptive Paths