Explainable Model

Explainable models aim to make the decision-making processes of machine learning models transparent and understandable, addressing the "black box" problem inherent in many complex algorithms. Current research focuses on developing inherently interpretable models, such as those based on additive models, decision trees, and prototypical networks, as well as employing post-hoc explanation techniques like SHAP values and counterfactual analysis to interpret existing models. This pursuit of explainability is crucial for building trust in AI systems across diverse fields, from healthcare and finance to environmental science, enabling more reliable decision-making and facilitating greater understanding of complex phenomena.

Papers

June 18, 2022

Machine Learning in Sports: A Case Study on Using Explainable Models for Predicting Outcomes of Volleyball Matches
Abhinav Lalwani, Aman Saraiya, Apoorv Singh, Aditya Jain, Tirtharaj Dash
Machine Learning Deep Neural Network Human Prediction Multiple Outcome Explainable Model Sport Understanding Interpretable Rule

June 16, 2022

Explainable Models via Compression of Tree Ensembles
Siwen Yan, Sriraam Natarajan, Saket Joshi, Roni Khardon, Prasad Tadepalli
Linear Compression Ensemble Model Explainable Model Tree Ensemble Probabilistic Logic Relational Datasets

May 9, 2022

Visualization of Decision Trees based on General Line Coordinates to Support Explainable Models
Alex Worland, Sridevi Wagle, Boris Kovalerchuk
Machine Learning Machine Learning Model Inherent Interpretability Decision Tree Interpretable Model Interactive Visualization Explainable Model

February 14, 2022

FOLD-RM: A Scalable, Efficient, and Explainable Inductive Learning Algorithm for Multi-Category Classification of Mixed Data
Huaduo Wang, Farhad Shakerin, Gopal Gupta
Potential Scalability Model Interpretability Explainable Model Inductive Learning Mixed Data Multi Category Fold Rm

December 7, 2021

Training Deep Models to be Explained with Fewer Examples
Tomoharu Iwata, Yuya Yoshikawa
Fewer Example Explainable Model Training Deep Explanation Model Example Based

December 1, 2021

First Steps of an Approach to the ARC Challenge based on Descriptive Grid Models and the Minimum Description Length Principle
Sébastien Ferré
Constructive Approach Explainable Model Reasoning Corpus Grid Based Minimum Description Length First Step

August 5, 2021

Mixture of Linear Models Co-supervised by Deep Neural Networks
Beomseok Seo, Lin Lin, Jia Li
Deep Neural Network Inherent Interpretability Mixture Component Explainable Model Linear Model Discriminative Model

Explainable Model

Papers

Machine Learning in Sports: A Case Study on Using Explainable Models for Predicting Outcomes of Volleyball Matches

Explainable Models via Compression of Tree Ensembles

Visualization of Decision Trees based on General Line Coordinates to Support Explainable Models

FOLD-RM: A Scalable, Efficient, and Explainable Inductive Learning Algorithm for Multi-Category Classification of Mixed Data

Training Deep Models to be Explained with Fewer Examples

First Steps of an Approach to the ARC Challenge based on Descriptive Grid Models and the Minimum Description Length Principle

Mixture of Linear Models Co-supervised by Deep Neural Networks