Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Su-In Lee

Explaining a Series of Models by Propagating Local Feature Attributions


Apr 30, 2021
Hugh Chen, Scott M. Lundberg, Su-In Lee


  Access Paper or Ask Questions

Improving KernelSHAP: Practical Shapley Value Estimation via Linear Regression


Dec 02, 2020
Ian Covert, Su-In Lee


  Access Paper or Ask Questions

Explaining by Removing: A Unified Framework for Model Explanation


Nov 21, 2020
Ian Covert, Scott Lundberg, Su-In Lee

* arXiv admin note: text overlap with arXiv:2011.03623 

  Access Paper or Ask Questions

Feature Removal Is a Unifying Principle for Model Explanation Methods


Nov 06, 2020
Ian Covert, Scott Lundberg, Su-In Lee


  Access Paper or Ask Questions

True to the Model or True to the Data?


Jun 29, 2020
Hugh Chen, Joseph D. Janizek, Scott Lundberg, Su-In Lee


  Access Paper or Ask Questions

Understanding Global Feature Contributions Through Additive Importance Measures


Apr 01, 2020
Ian Covert, Scott Lundberg, Su-In Lee


  Access Paper or Ask Questions

Explaining Explanations: Axiomatic Feature Interactions for Deep Networks


Feb 12, 2020
Joseph D. Janizek, Pascal Sturmfels, Su-In Lee


  Access Paper or Ask Questions

Deep Transfer Learning for Physiological Signals


Feb 12, 2020
Hugh Chen, Scott Lundberg, Gabe Erion, Jerry H. Kim, Su-In Lee


  Access Paper or Ask Questions

Learning Deep Attribution Priors Based On Prior Knowledge


Feb 07, 2020
Ethan Weinberger, Joseph Janizek, Su-In Lee


  Access Paper or Ask Questions

An Adversarial Approach for the Robust Classification of Pneumonia from Chest Radiographs


Jan 13, 2020
Joseph D. Janizek, Gabriel Erion, Alex J. DeGrave, Su-In Lee


  Access Paper or Ask Questions

Learned Feature Attribution Priors


Dec 20, 2019
Ethan Weinberger, Joseph Janizek, Su-In Lee


  Access Paper or Ask Questions

Explaining Models by Propagating Shapley Values of Local Components


Nov 27, 2019
Hugh Chen, Scott Lundberg, Su-In Lee

* 4 pages and references 

  Access Paper or Ask Questions

Learning Explainable Models Using Attribution Priors


Jun 25, 2019
Gabriel Erion, Joseph D. Janizek, Pascal Sturmfels, Scott Lundberg, Su-In Lee


  Access Paper or Ask Questions

Explainable AI for Trees: From Local Explanations to Global Understanding


May 11, 2019
Scott M. Lundberg, Gabriel Erion, Hugh Chen, Alex DeGrave, Jordan M. Prutkin, Bala Nair, Ronit Katz, Jonathan Himmelfarb, Nisha Bansal, Su-In Lee


  Access Paper or Ask Questions

Consistent Individualized Feature Attribution for Tree Ensembles


Jun 18, 2018
Scott M. Lundberg, Gabriel G. Erion, Su-In Lee

* Follow-up to 2017 ICML Workshop arXiv:1706.06060 

  Access Paper or Ask Questions

Consistent feature attribution for tree ensembles


Feb 17, 2018
Scott M. Lundberg, Su-In Lee

* presented at 2017 ICML Workshop on Human Interpretability in Machine Learning (WHI 2017), Sydney, NSW, Australia 

  Access Paper or Ask Questions

Hybrid Gradient Boosting Trees and Neural Networks for Forecasting Operating Room Data


Jan 24, 2018
Hugh Chen, Scott Lundberg, Su-In Lee

* Presented at Machine Learning for Health Workshop: 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA 

  Access Paper or Ask Questions

Anesthesiologist-level forecasting of hypoxemia with only SpO2 data using deep learning


Dec 02, 2017
Gabriel Erion, Hugh Chen, Scott M. Lundberg, Su-In Lee

* To be presented at Machine Learning for Health Workshop: 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA 

  Access Paper or Ask Questions

A Unified Approach to Interpreting Model Predictions


Nov 25, 2017
Scott Lundberg, Su-In Lee

* To appear in NIPS 2017 

  Access Paper or Ask Questions

Checkpoint Ensembles: Ensemble Methods from a Single Training Process


Oct 09, 2017
Hugh Chen, Scott Lundberg, Su-In Lee

* 7 pages, 4 figures, under review AAAI 

  Access Paper or Ask Questions

An unexpected unity among methods for interpreting model predictions


Dec 08, 2016
Scott Lundberg, Su-In Lee

* Presented at NIPS 2016 Workshop on Interpretable Machine Learning in Complex Systems 

  Access Paper or Ask Questions

Learning Graphical Models With Hubs


Aug 09, 2014
Kean Ming Tan, Palma London, Karthik Mohan, Su-In Lee, Maryam Fazel, Daniela Witten


  Access Paper or Ask Questions

Node-Based Learning of Multiple Gaussian Graphical Models


Jan 22, 2014
Karthik Mohan, Palma London, Maryam Fazel, Daniela Witten, Su-In Lee

* 42 pages, 16 figures. Accepted to JMLR, 2014 

  Access Paper or Ask Questions