Local Interpretability

Local interpretability in machine learning focuses on explaining individual predictions made by complex models, such as deep neural networks and time series transformers, to enhance trust and facilitate understanding. Current research emphasizes developing methods that provide faithful and robust explanations, often using techniques like SHAP values, LIME, and rule-based ensembles, and exploring how to effectively evaluate the quality of these explanations. This area is crucial for deploying machine learning models in high-stakes domains like healthcare and finance, where understanding model decisions is paramount for responsible use and building trust.

Papers

January 26, 2024

Interpreting Time Series Transformer Models and Sensitivity Analysis of Population Age Groups to COVID-19 Infections
Md Khairul Islam, Tyler Valentine, Timothy Joowon Sue, Ayush Karmacharya, Luke Neil Benham, Zhengguang Wang, Kingsley Kim, Judy Fox
Time Series Covid 19 Local Interpretability Time Series Transformer Model

October 30, 2023

Faithful and Robust Local Interpretability for Textual Predictions
Gianluigi Lopardo, Frederic Precioso, Damien Garreau
Inherent Interpretability Robust Version Counterfactual Explanation Interpretable Classifier Robust Explanation Textual Model Local Interpretability

September 16, 2023

Extracting Interpretable Local and Global Representations from Attention on Time Series
Leonid Schwenke, Martin Atzmueller
Time Series Inherent Interpretability High Explainability Human Attention Interpretability Method Transformer Attention Global Representation Local Interpretability

July 16, 2023

SHAMSUL: Systematic Holistic Analysis to investigate Medical Significance Utilizing Local interpretability methods in deep learning for chest radiography pathology prediction
Mahbub Ul Alam, Jaakko Hollmén, Jón Rúnar Baldvinsson, Rahim Rahmani
Deep Learning Inherent Interpretability Interpretability Method Clinical Application Local Interpretability Local Interpretable

June 20, 2023

Learning Locally Interpretable Rule Ensemble
Kentaro Kanamori
Interpretable Model Interpretable Rule Local Interpretability Rule Ensemble

March 29, 2023

Local Interpretability of Random Forests for Multi-Target Regression
Avraam Bardos, Nikolaos Mylonas, Ioannis Mollas, Grigorios Tsoumakas
Inherent Interpretability Random Forest Random Forest Model Local Interpretability Multi Target

March 2, 2023

Feature Perturbation Augmentation for Reliable Evaluation of Importance Estimators in Neural Networks
Lennart Brocki, Neo Christopher Chung
Neural Network Importance Estimation Perturbation Augmentation Local Interpretability Post Hoc Interpretability Perturbation Artifact

December 7, 2022

Truthful Meta-Explanations for Local Interpretability of Machine Learning Models
Ioannis Mollas, Nick Bassiliades, Grigorios Tsoumakas
Machine Learning Model Inherent Interpretability Complex Machine Learning Local Interpretability Machine Learning Based System

December 1, 2022

Implicit Mixture of Interpretable Experts for Global and Local Interpretability
Nathan Elazar, Kerry Taylor
World Event Interpretable Image Expert Annotated Global Interpretability Local Interpretability Finite Mixture Intelligent Routing

November 3, 2022

A $k$-additive Choquet integral-based approach to approximate the SHAP values for local interpretability in machine learning
Guilherme Dean Pelegrina, Leonardo Tomazeli Duarte, Michel Grabisch
Machine Learning Shapley Value Shapley Interaction Local Interpretability SHAP Value SHAP Clustering Integral Regression Choquet Integral

August 1, 2022

Interpretable Time Series Clustering Using Local Explanations
Ozan Ozyegen, Nicholas Prayogo, Mucahit Cevik, Ayse Basar
Interpretability Method Local Explanation Time Series Clustering State of the Art Clustering Local Interpretability

May 5, 2022

Development of Interpretable Machine Learning Models to Detect Arrhythmia based on ECG Data
Shourya Verma
Inherent Interpretability Development Activity Interpretable Machine Learning Interpretability Method Electrocardiogram Data Local Interpretability Arrhythmia Type

April 7, 2022

Using Decision Tree as Local Interpretable Model in Autoencoder-based LIME
Niloofar Ranjbar, Reza Safabakhsh
Inherent Interpretability Interpretable Model Local Interpretable Model Agnostic Explanation Local Interpretability Local Interpretable

March 8, 2022

Logic-based AI for Interpretable Board Game Winner Prediction with Tsetlin Machine
Charul Giri, Ole-Christoffer Granmo, Herke van Hoof, Christian D. Blakely
Inherent Interpretability Propositional Logic Tsetlin Machine Game State Local Interpretability Connection Game

January 4, 2022

McXai: Local model-agnostic explanation as two games
Yiran Huang, Nicole Schaal, Michael Hefenbrock, Yexu Zhou, Till Riedel, Likun Fang, Michael Beigl
Black Box Monte Carlo Tree Search Black Box Model Video Game Local Interpretable Model Agnostic Explanation Black Box Machine Learning Model Local Interpretability

Local Interpretability

Papers

Interpreting Time Series Transformer Models and Sensitivity Analysis of Population Age Groups to COVID-19 Infections

Faithful and Robust Local Interpretability for Textual Predictions

Extracting Interpretable Local and Global Representations from Attention on Time Series

SHAMSUL: Systematic Holistic Analysis to investigate Medical Significance Utilizing Local interpretability methods in deep learning for chest radiography pathology prediction

Learning Locally Interpretable Rule Ensemble

Local Interpretability of Random Forests for Multi-Target Regression

Feature Perturbation Augmentation for Reliable Evaluation of Importance Estimators in Neural Networks

Truthful Meta-Explanations for Local Interpretability of Machine Learning Models

Implicit Mixture of Interpretable Experts for Global and Local Interpretability

A $k$-additive Choquet integral-based approach to approximate the SHAP values for local interpretability in machine learning

Interpretable Time Series Clustering Using Local Explanations

Development of Interpretable Machine Learning Models to Detect Arrhythmia based on ECG Data

Using Decision Tree as Local Interpretable Model in Autoencoder-based LIME

Logic-based AI for Interpretable Board Game Winner Prediction with Tsetlin Machine

McXai: Local model-agnostic explanation as two games