Parameterized Explainer for Graph Neural Network

Last update: Dec 12, 2022

Overview

PGExplainer

This is a Tensorflow implementation of the paper: Parameterized Explainer for Graph Neural Network

https://arxiv.org/abs/2011.04573

NeurIPS 2020

Requirements

Python 3.6.8
tensorflow 2.0
networkx

References

@article{luo2020parameterized,
  title={Parameterized Explainer for Graph Neural Network},
  author={Luo, Dongsheng and Cheng, Wei and Xu, Dongkuan and Yu, Wenchao and Zong, Bo and Chen, Haifeng and Zhang, Xiang},
  journal={Advances in Neural Information Processing Systems},
  volume={33},
  year={2020}
}

Pytorch Implementation

Here are several re-implementations and reproduction reports from other groups. Thanks very much these researchers for re-implementing PGExplainer to make it more easy to use!

[Re] Parameterized Explainer for Graph Neural Network

https://zenodo.org/record/4834242/files/article.pdf

Code:

https://github.com/LarsHoldijk/RE-ParameterizedExplainerForGraphNeuralNetworks

Note that in this report, they adopt different GCN models with our implementation.

Reproducing: Parameterized Explainer for Graph NeuralNetwork

https://openreview.net/forum?id=tt04glo-VrT

Code:

https://openreview.net/attachment?id=tt04glo-VrT&name=supplementary_material

https://github.com/divelab/DIG/tree/main/dig/xgraph/PGExplainer

Parameterized Explainer for Graph Neural Network

Related tags

Overview

PGExplainer

Requirements

References

Pytorch Implementation

Owner

Dongsheng Luo

Use MATLAB to simulate the signal and extract features. Use PyTorch to build and train deep network to do spectrum sensing.

I explore rock vs. mine prediction using a SONAR dataset

Towards Boosting the Accuracy of Non-Latin Scene Text Recognition

Experimental solutions to selected exercises from the book [Advances in Financial Machine Learning by Marcos Lopez De Prado]

These are the materials for the paper "Few-Shot Out-of-Domain Transfer Learning of Natural Language Explanations"

Data-depth-inference - Data depth inference with python

We envision models that are pre-trained on a vast range of domain-relevant tasks to become key for molecule property prediction

Efficient 3D human pose estimation in video using 2D keypoint trajectories

Official PyTorch implementation of "Preemptive Image Robustification for Protecting Users against Man-in-the-Middle Adversarial Attacks" (AAAI 2022)

PyTorch implementation of paper "IBRNet: Learning Multi-View Image-Based Rendering", CVPR 2021.

JFB: Jacobian-Free Backpropagation for Implicit Models

Smart edu-autobooking - Johnson @ DMI-UNICT study room self-booking system

An Approach to Explore Logistic Regression Models

An API-first distributed deployment system of deep learning models using timeseries data to analyze and predict systems behaviour

Train a deep learning net with OpenStreetMap features and satellite imagery.

Citation Intent Classification in scientific papers using the Scicite dataset an Pytorch

Torch code for our CVPR 2018 paper "Residual Dense Network for Image Super-Resolution" (Spotlight)

Self-Supervised Vision Transformers Learn Visual Concepts in Histopathology (LMRL Workshop, NeurIPS 2021)

ObjectDetNet is an easy, flexible, open-source object detection framework

PyTorch code for Composing Partial Differential Equations with Physics-Aware Neural Networks