Local Interpretable

Local interpretable model-agnostic explanations (LIME) aim to make the predictions of complex machine learning models, often "black boxes," understandable by providing local explanations for individual predictions. Current research focuses on improving the stability, accuracy, and fidelity of LIME and related methods like SHAP, often by employing alternative model architectures (e.g., decision trees, Bayesian regression) within the explanation framework or by developing inherently interpretable models. This work is crucial for building trust in AI systems, particularly in high-stakes domains like medicine, where understanding the reasoning behind predictions is essential for responsible deployment and clinical decision-making.

Papers

June 8, 2024

Attri-Net: A Globally and Locally Inherently Interpretable Model for Multi-Label Classification Using Class-Specific Counterfactuals
Susu Sun, Stefano Woerner, Andreas Maier, Lisa M. Koch, Christian F. Baumgartner
Inherent Interpretability Multi Label Classification Interpretable Model Global Explanation Attribution Map Consistent Counterfactuals Local Interpretable

June 1, 2024

Alternative Methods to SHAP Derived from Properties of Kernels: A Note on Theoretical Analysis
Kazuhiro Hiraki, Shinichi Ishihara, Junnosuke Shino
Theoretical Analysis Short Note Many Property Small Kernel Shapley Additive Explanation Current Method Cooperative Game Theory Model Agnostic Explanation Additive Feature Attribution Local Interpretable

November 27, 2023

GLIME: General, Stable and Local LIME Explanation
Zeren Tan, Yang Tian, Jian Li
General Text Local Interpretable Model Agnostic Explanation Model Agnostic Explanation Black Box Machine Learning Model Local Interpretable Quantum State Fidelity

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

April 29, 2023

EBLIME: Enhanced Bayesian Local Interpretable Model-agnostic Explanations
Yuhao Zhong, Anirban Bhattacharya, Satish Bukkapatnam
Posterior Inference Feature Importance Ridge Regression Model Agnostic Explanation Black Box Machine Learning Model Local Interpretable

November 28, 2022

Explaining Deep Convolutional Neural Networks for Image Classification by Evolving Local Interpretable Model-agnostic Explanations
Bin Wang, Wenbin Pei, Bing Xue, Mengjie Zhang
Image Classification Deep Convolutional Neural Network Supervised ImageNet ImageNet Dataset Convolutional Neural Network Model Model Agnostic Explanation Local Interpretable

November 1, 2022

Transfer learning and Local interpretable model agnostic based visual approach in Monkeypox Disease Detection and Classification: A Deep Learning insights
Md Manjurul Ahsan, Tareque Abu Abdullah, Md Shahin Ali, Fatematuj Jahora, Md Khairul Islam, Amin G. Alhashim, Kishor Datta Gupta
Deep Learning Transfer Learning Disease Prediction Disease Detection Model Monkeypox Disease Monkeypox Disease Detection Local Interpretable

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

Local Interpretable

Papers

Attri-Net: A Globally and Locally Inherently Interpretable Model for Multi-Label Classification Using Class-Specific Counterfactuals

Alternative Methods to SHAP Derived from Properties of Kernels: A Note on Theoretical Analysis

GLIME: General, Stable and Local LIME Explanation

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

EBLIME: Enhanced Bayesian Local Interpretable Model-agnostic Explanations

Explaining Deep Convolutional Neural Networks for Image Classification by Evolving Local Interpretable Model-agnostic Explanations

Transfer learning and Local interpretable model agnostic based visual approach in Monkeypox Disease Detection and Classification: A Deep Learning insights

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