Skip to content
This is a PyTorch implementation of the GeniePath model in <GeniePath: Graph Neural Networks with Adaptive Receptive Paths> (https://arxiv.org/abs/1802.00910)
Python
Branch: master
Clone or download
Latest commit 1c44a5f Sep 22, 2019
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
doc Add Readme Jun 5, 2019
.gitignore
LICENSE Initial commit May 29, 2019
README.md Update README.md Sep 22, 2019
model_gat.py Add init commit Jun 4, 2019
model_geniepath.py
ppi_gat.py Add init commit Jun 4, 2019
ppi_geniepath.py Add Readme Jun 5, 2019
requirements.txt Add Readme Jun 5, 2019

README.md

GeniePath-pytorch

This is a PyTorch implementation of the GeniePath model in GeniePath: Graph Neural Networks with Adaptive Receptive Paths

GeniePath, a scalable approach for learning adap- tive receptive fields of neural networks defined on permuta- tion invariant graph data. In GeniePath, we propose an adap- tive path layer consists of two complementary functions de- signed for breadth and depth exploration respectively, where the former learns the importance of different sized neighbor- hoods, 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 ex- periments compared with competitive methods show that our approaches yield state-of-the-art results on large graphs

Model

Requirements

Usage

Install packages

pip install -r requirements.txt
# pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple

Choose Model

in ppi_geniepath.py

# from model_geniepath import GeniePath as Net
from model_geniepath import GeniePathLazy as Net

Run

python ppi_geniepath.py

TODO

  • Finish the rough implementation, f1_score: 0.9709 for GeniePath, 0.9762 for GeniePathLazy (dim = 256, lstm_hidden = 256).
  • Tune the model

Reference

You can’t perform that action at this time.