GeniePath: Graph Neural Networks with Adaptive Receptive Paths

Authors

  • 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

DOI:

https://doi.org/10.1609/aaai.v33i01.33014424

Abstract

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.

Downloads

Published

2019-07-17

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. https://doi.org/10.1609/aaai.v33i01.33014424

Issue

Section

AAAI Technical Track: Machine Learning