GeniePath: Graph Neural Networks with Adaptive Receptive Paths

Ziqi Liu, Chaochao Chen, Longfei Li, Jun Zhou, Xiaolong Li, Le Song, Yuan Qi

AAAI 2019 pp. 4424-4431

doi:10.1609/AAAI.V33I01.33014424 /aaai/2019/liu2019aaai-geniepath/

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.

PDF AAAI Semantic Scholar

Cite

Text

Liu et al. "GeniePath: Graph Neural Networks with Adaptive Receptive Paths." AAAI Conference on Artificial Intelligence, 2019. doi:10.1609/AAAI.V33I01.33014424

Markdown

[Liu et al. "GeniePath: Graph Neural Networks with Adaptive Receptive Paths." AAAI Conference on Artificial Intelligence, 2019.](https://mlanthology.org/aaai/2019/liu2019aaai-geniepath/) doi:10.1609/AAAI.V33I01.33014424

BibTeX

@inproceedings{liu2019aaai-geniepath,
  title     = {{GeniePath: Graph Neural Networks with Adaptive Receptive Paths}},
  author    = {Liu, Ziqi and Chen, Chaochao and Li, Longfei and Zhou, Jun and Li, Xiaolong and Song, Le and Qi, Yuan},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2019},
  pages     = {4424-4431},
  doi       = {10.1609/AAAI.V33I01.33014424},
  url       = {https://mlanthology.org/aaai/2019/liu2019aaai-geniepath/}
}