explainability.md

Explainability

• A Unified Approach to Interpreting Model Predictions (NeurIPS 2017)

  • Scott M. Lundberg, Su-In Lee
  • [Paper]
  • [Code]

• L-Shapley and C-Shapley: Efficient Model Interpretation for Structured Data (ICLR 2019)

  • Jianbo Chen, Le Song, Martin J. Wainwright, Michael I. Jordan
  • [Paper]
  • [Code]

• Explaining Deep Neural Networks with a Polynomial Time Algorithm for Shapley Value Approximation (ICML 2019)

  • Marco Ancona, Cengiz Öztireli, Markus H. Gross
  • [Paper]
  • [Code]

• The Explanation Game: Explaining Machine Learning Models Using Shapley Values (MAKE 2020)

  • Luke Merrick, Ankur Taly
  • [Paper]
  • [Code]

• Shapley Values and Meta-Explanations for Probabilistic Graphical Model Inference (CIKM 2020)

  • Yifei Liu, Chao Chen, Yazheng Liu, Xi Zhang, Sihong Xie
  • [Paper]

• Problems with Shapley-value-based explanations as feature importance measures (ICML 2020)

  • I. Elizabeth Kumar, Suresh Venkatasubramanian, Carlos Scheidegger, Sorelle A. Friedler
  • [Paper]

• The Many Shapley Values for Model Explanation (ICML 2020)

  • Mukund Sundararajan, Amir Najmi
  • [Paper]

• The Shapley Taylor Interaction Index (ICML 2020)

  • Mukund Sundararajan, Kedar Dhamdhere, Ashish Agarwal
  • [Paper]

• Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainability (NIPS 2020)

  • Christopher Frye, Colin Rowat, Ilya Feige
  • [Paper]
  • [Code]

• Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Models (NIPS 2020)

  • Tom Heskes, Evi Sijben, Ioan Gabriel Bucur, Tom Claassen
  • [Paper]

• Neuron Shapley: Discovering the Responsible Neurons (NIPS 2020)

  • Amirata Ghorbani, James Y. Zou
  • [Paper]
  • [Code]

• Interpreting Multivariate Shapley Interactions in DNNs (AAAI 2021)

  • Hao Zhang, Yichen Xie, Longjie Zheng, Die Zhang, Quanshi Zhang
  • [Paper]
  • [Code]

• Shapley Flow: A Graph-based Approach to Interpreting Model Predictions (AISTATS 2021)

  • Jiaxuan Wang, Jenna Wiens, Scott M. Lundberg
  • [Paper]
  • [Code]

• Improving KernelSHAP: Practical Shapley Value Estimation Using Linear Regression (AISTATS 2021)

  • Ian Covert, Su-In Lee
  • [Paper]
  • [Code]

• Shapley explainability on the data manifold (ICLR 2021)

  • Christopher Frye, Damien de Mijolla, Tom Begley, Laurence Cowton, Megan Stanley, Ilya Feige
  • [Paper]

• Shapley Explanation Networks (ICLR 2021)

  • Rui Wang, Xiaoqian Wang, David I. Inouye
  • [Paper]
  • [Code]

• Flow-based Attribution in Graphical Models: A Recursive Shapley Approach (ICML 2021)

  • Raghav Singal, George Michailidis, Hoiyi Ng
  • [Paper]

• GraphSVX: Shapley Value Explanations for Graph Neural Networks (ECML PKDD 2021)

  • Alexandre Duval and Fragkiskos Malliaros
  • [Paper]
  • [Code]

• Threading the Needle of On and Off-Manifold Value Functions for Shapley Explanations (AISTATS 2022)

  • Chih-Kuan Yeh, Kuan-Yun Lee, Frederick Liu, Pradeep Ravikumar
  • [Paper]

• Accurate Shapley Values for explaining tree-based models (AISTATS 2022)

  • Salim I. Amoukou, Tangi Salaün, Nicolas J.-B. Brunel
  • [Paper]
  • [Code]

• FastSHAP: Real-Time Shapley Value Estimation (ICLR 2022)

  • Neil Jethani, Mukund Sudarshan, Ian Covert, Su-In Lee, Rajesh Ranganath
  • [Paper]
  • [Code]

• Accelerating Shapley Explanation via Contributive Cooperator Selection (ICML 2022)

  • Guanchu Wang, Yu-Neng Chuang, Mengnan Du, Fan Yang, Quan Zhou, Pushkar Tripathi, Xuanting Cai, Xia Hu
  • [Paper]
  • [Code]

• Algorithms to Estimate Shapley Value Feature Attributions (Arxiv 2022)

  • Hugh Chen, Ian C. Covert, Scott M. Lundberg, Su-In Lee
  • [Paper]