GeniePath: Graph Neural Networks with Adaptive Receptive Paths


  • Ziqi Liu Ant Financial Services Group
  • Chaochao Chen Ant Financial Services Group
  • Longfei Li Ant Financial Services Group
  • Jun Zhou Ant Financial Services Group
  • Xiaolong Li Ant Financial Services Group
  • Le Song Ant Financial Services Group
  • Yuan Qi Ant Financial Services Group



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 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. Our method works in both transductive and inductive settings, and extensive experiments compared with competitive methods show that our approaches yield state-of-the-art results on large graphs.




How to Cite

Liu, Z., Chen, C., Li, L., Zhou, J., Li, X., Song, L., & Qi, Y. (2019). GeniePath: Graph Neural Networks with Adaptive Receptive Paths. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 4424-4431.



AAAI Technical Track: Machine Learning