Quantifying Model Complexity via Functional Decomposition for Better
Post-Hoc Interpretability

v1v2 (latest)

Quantifying Model Complexity via Functional Decomposition for Better Post-Hoc Interpretability

8 April 2019

Christoph Molnar

Giuseppe Casalicchio

ArXiv (abs)PDF HTML

Papers citing "Quantifying Model Complexity via Functional Decomposition for Better Post-Hoc Interpretability"

18 / 18 papers shown

Title
Multi-Objective Optimization of Performance and Interpretability of Tabular Supervised Machine Learning Models Lennart Schneider B. Bischl Janek Thomas 96 7 0 17 Jul 2023
Improving Interpretability via Explicit Word Interaction Graph Layer Arshdeep Sekhon Hanjie Chen A. Shrivastava Zhe Wang Yangfeng Ji Yanjun Qi AI4CE MILM 70 6 0 03 Feb 2023
Mind the Gap: Measuring Generalization Performance Across Multiple Objectives Matthias Feurer Katharina Eggensperger Eddie Bergman Florian Pfisterer B. Bischl Frank Hutter 116 5 0 08 Dec 2022
Comparing Explanation Methods for Traditional Machine Learning Models Part 1: An Overview of Current Methods and Quantifying Their Disagreement Montgomery Flora Corey K. Potvin A. McGovern Shawn Handler FAtt 97 18 0 16 Nov 2022
DALE: Differential Accumulated Local Effects for efficient and accurate global explanations Vasilis Gkolemis Theodore Dalamagas Christos Diou 56 13 0 10 Oct 2022
From plane crashes to algorithmic harm: applicability of safety engineering frameworks for responsible ML Shalaleh Rismani Renee Shelby A. Smart Edgar W. Jatho Joshua A. Kroll AJung Moon Negar Rostamzadeh 106 42 0 06 Oct 2022
Explainability in Process Outcome Prediction: Guidelines to Obtain Interpretable and Faithful Models Alexander Stevens Johannes De Smedt XAI FaML 113 14 0 30 Mar 2022
Hyperparameter Optimization: Foundations, Algorithms, Best Practices and Open Challenges B. Bischl Martin Binder Michel Lang Tobias Pielok Jakob Richter ... Theresa Ullmann Marc Becker A. Boulesteix Difan Deng Marius Lindauer 250 514 0 13 Jul 2021
Explainable Artificial Intelligence Approaches: A Survey Sheikh Rabiul Islam W. Eberle S. Ghafoor Mohiuddin Ahmed XAI 87 104 0 23 Jan 2021
CDT: Cascading Decision Trees for Explainable Reinforcement Learning Zihan Ding Pablo Hernandez-Leal G. Ding Changjian Li Ruitong Huang 65 21 0 15 Nov 2020
Interpretable Machine Learning -- A Brief History, State-of-the-Art and Challenges Christoph Molnar Giuseppe Casalicchio B. Bischl AI4TS AI4CE 114 405 0 19 Oct 2020
The role of explainability in creating trustworthy artificial intelligence for health care: a comprehensive survey of the terminology, design choices, and evaluation strategies A. Markus J. Kors P. Rijnbeek 91 472 0 31 Jul 2020
General Pitfalls of Model-Agnostic Interpretation Methods for Machine Learning Models Christoph Molnar Gunnar Konig J. Herbinger Timo Freiesleben Susanne Dandl Christian A. Scholbeck Giuseppe Casalicchio Moritz Grosse-Wentrup B. Bischl FAtt AI4CE 85 140 0 08 Jul 2020
What Would You Ask the Machine Learning Model? Identification of User Needs for Model Explanations Based on Human-Model Conversations Michal Kuzba P. Biecek HAI 55 22 0 07 Feb 2020
Towards Quantification of Explainability in Explainable Artificial Intelligence Methods Sheikh Rabiul Islam W. Eberle S. Ghafoor XAI 82 43 0 22 Nov 2019
Multi-Objective Automatic Machine Learning with AutoxgboostMC Florian Pfisterer Stefan Coors Janek Thomas B. Bischl 65 17 0 28 Aug 2019
Proposed Guidelines for the Responsible Use of Explainable Machine Learning Patrick Hall Navdeep Gill N. Schmidt SILM XAI FaML 80 29 0 08 Jun 2019
Disentangled Attribution Curves for Interpreting Random Forests and Boosted Trees Summer Devlin Chandan Singh W. James Murdoch Bin Yu FAtt 62 14 0 18 May 2019