Awesome Explainable Graph Reasoning
A collection of research papers and software related to explainability in graph machine learning.
Contents
License
A collection of research papers and software related to explainability in graph machine learning.
License
Hi all, I've added a new reference to a paper of mine related to counterfactual explanations for molecule predictions. I hope this is appreciated :)
Link to paper: https://arxiv.org/abs/2104.08060
You might want to double check this commit is ok - I added a new sub-heading called concept based methods which was not covered by the survey paper the rest of the approaches are categorised into.
Two papers on rule-based reasoning:
And one application note on a web application for visualizing predictions and their explanations using made my the approaches above:
The work 'Evaluating Attribution for Graph Neural Networks' is particularly useful because of its approach as a benchmarking. It comprises several attribution techniques and GNN architectures.
Hi, I have been impressed about how fast is this field growing. As I continue reading and learning, I will contribute with papers to make this list even better.
In particular, @flyingdoog is maintaining a list with the papers (grouped by year) at https://github.com/flyingdoog/awesome-graph-explainability-papers that can be interesting to review
pyBreakDown Python implementation of breakDown package (https://github.com/pbiecek/breakDown). Docs: https://pybreakdown.readthedocs.io. Requirements
CapsNet-Visualization For more information on capsule networks check out my Medium articles here and here. Setup Use pip to install the required pytho
lime This project is about explaining what machine learning classifiers (or models) are doing. At the moment, we support explaining individual predict
Anchor This repository has code for the paper High-Precision Model-Agnostic Explanations. An anchor explanation is a rule that sufficiently “anchors”
Delve is a Python package for analyzing the inference dynamics of your PyTorch model.
MapExtrackt Convolutional Neural Networks Are Beautiful We all take our eyes for granted, we glance at an object for an instant and our brains can ide
Lucid Lucid is a collection of infrastructure and tools for research in neural network interpretability. We're not currently supporting tensorflow 2!
dtreeviz : Decision Tree Visualization Description A python library for decision tree visualization and model interpretation. Currently supports sciki
TensorFlow Model Analysis TensorFlow Model Analysis (TFMA) is a library for evaluating TensorFlow models. It allows users to evaluate their models on
Documentation | External Resources | Research Paper Shapley is a Python library for evaluating binary classifiers in a machine learning ensemble. The
Alibi is an open source Python library aimed at machine learning model inspection and interpretation. The focus of the library is to provide high-qual
Mol Viewer This is a simple package wrapping py3dmol for a single command visualization of a RDKit molecule and its conformations (embed as Conformer
Contrastive Explanation (Foil Trees) Contrastive and counterfactual explanations for machine learning (ML) Marcel Robeer (2018-2020), TNO/Utrecht Univ
Tool for visualizing attention in the Transformer model (BERT, GPT-2, Albert, XLNet, RoBERTa, CTRL, etc.)
TreeInterpreter Package for interpreting scikit-learn's decision tree and random forest predictions. Allows decomposing each prediction into bias and
Visualizing the Loss Landscape of Neural Nets This repository contains the PyTorch code for the paper Hao Li, Zheng Xu, Gavin Taylor, Christoph Studer
Skater Skater is a unified framework to enable Model Interpretation for all forms of model to help one build an Interpretable machine learning system
tensorboardX Write TensorBoard events with simple function call. The current release (v2.1) is tested on anaconda3, with PyTorch 1.5.1 / torchvision 0
ModelChimp What is ModelChimp? ModelChimp is an experiment tracker for Deep Learning and Machine Learning experiments. ModelChimp provides the followi
Welcome to Scikit-plot Single line functions for detailed visualizations The quickest and easiest way to go from analysis... ...to this. Scikit-plot i