Deep Learning and Graph Neural Network Interpretable papers and codes.
Part One: Deep Learning Interpretable Survey
Title
Date
Links
First Author
Code
A Survey on Explainable Artificial Intelligence (XAI): towards Medical XAI
2020
CoRR
Erico Tjoa
No
A Survey on Techniques, Applications and Security of Machine Learning Interpretability
2019
计算机研究与发展
纪守领
No
Visual Interpretability for Deep Learning: a Survey
2018
Frontiers of Information Technology & Electronic Engineering
Quanshi Zhang
No
Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI)
2018
IEEE Access
Amina Adadi
No
Interpretable Machine Learning: The fuss, the concrete and the questions
2017
ICML
Been Kim
No
Part Two: Deep Learning Interpretable Papers
Title
Date
Links
First Author
Model
SAUNet: Shape Attentive U-Net for Interpretable Medical Image Segmentation
2020
MICCAI
Jesse Sun
U-Net
Local Interpretable Model-Agnostic Explanations for Classification of Lymph Node Metastases
2019
sensors
Iam Palatnik de Sousa
---
Uncertainty Modeling and Interpretability In Convolutional Neural Networks for Polyp Segmentation
2018
IEEE International Workshop on Machine Learning For Signal Processing
Kristoffer Wickstrøm
No
Part Three: Graph Neural Network Interpretable Survey
Title
Date
Links
First Author
Code
Explainability Methods for Graph Convolutional Neural Networks
2019
CVPR
Phillip E.Pope
github
Explainability Techniques for Graph Convolutional Networks
2019
ICML
Federico Baldassarre
github
Part Four: Graph Neural Network Interpretable Papers
Title
Date
Links
First Author
Code
Interpretable Neuron Structuring with Graph Spectral Regularization
2020
IDA
Alexander Tong
github
XGNN: Towards Model-Level Explanations of Graph Neural Networks
2020
KDD
Hao Yuan
No
Interpretable and Efficient Heterogeneous Graph Convolutional Network
2020
CoRR
Yaming Yang
Pytorch
Towards Interpretable Sparse Graph Representation Learning with Laplacian Pooling
2020
CoRR
Emmanuel Noutahi
No
GNNExplainer: Generating Explanations for Graph Neural Networks
2019
NeurIPS
Rex Ying
github
Factor Graph Neural Network
2019
CoRR
Zhen Zhang
github
Discovering Molecular Functional Groups Using Graph Convolutional Neural Networks
2019
CoRR
Philip E.Pope
No
BayesGrad: Explaining Predictions of Graph Convolutional Networks
2018
ICONIP
Hirotaka Akita
github
Part Five: Deep Learning Interpretable Scholars
Part Six: Technology Tools
1、Captum
Captum is a model interpretability and understanding library for PyTorch.
2、Convolutional Neural Network Visualizations
This repository contains a number of convolutional neural network visualization techniques implemented in PyTorch.