Causality-based Explanation of Classification Outcomes

We propose a simple definition of an explanation for the outcome of a classifier based on concepts from causality. We compare it with previously proposed notions of explanation, and study their complexity. We conduct an experimental evaluation with two real datasets from the financial domain.

[1]  Yang Liu,et al.  Actionable Recourse in Linear Classification , 2018, FAT.

[2]  Gabriel Erion,et al.  Explainable AI for Trees: From Local Explanations to Global Understanding , 2019, ArXiv.

[3]  Joseph Y. Halpern,et al.  Responsibility and Blame: A Structural-Model Approach , 2003, IJCAI.

[4]  Carlos Guestrin,et al.  "Why Should I Trust You?": Explaining the Predictions of Any Classifier , 2016, ArXiv.

[5]  Oluwasanmi Koyejo,et al.  Interpreting Black Box Predictions using Fisher Kernels , 2018, AISTATS.

[6]  Avanti Shrikumar,et al.  Learning Important Features Through Propagating Activation Differences , 2017, ICML.

[7]  Babak Salimi,et al.  From Causes for Database Queries to Repairs and Model-Based Diagnosis and Back , 2014, Theory of Computing Systems.

[8]  L. Shapley,et al.  The Shapley Value , 1994 .

[9]  Leslie G. Valiant,et al.  The Complexity of Enumeration and Reliability Problems , 1979, SIAM J. Comput..

[10]  Finale Doshi-Velez,et al.  A Roadmap for a Rigorous Science of Interpretability , 2017, ArXiv.

[11]  Yash Goyal,et al.  Explaining Classifiers with Causal Concept Effect (CaCE) , 2019, ArXiv.

[12]  Zachary Chase Lipton.  The mythos of model interpretability , 2016, ACM Queue.

[13]  Cynthia Rudin,et al.  Please Stop Explaining Black Box Models for High Stakes Decisions , 2018, ArXiv.

[14]  Hugh Chen,et al.  From local explanations to global understanding with explainable AI for trees , 2020, Nature Machine Intelligence.

[15]  Scott Lundberg,et al.  A Unified Approach to Interpreting Model Predictions , 2017, NIPS.

[16]  Joseph Y. Halpern,et al.  Causes and explanations: A structural-model approach , 2000 .

[17]  Joseph Y. Halpern,et al.  Causes and Explanations: A Structural-Model Approach. Part I: Causes , 2000, The British Journal for the Philosophy of Science.

[18]  James Zou,et al.  Towards Automatic Concept-based Explanations , 2019, NeurIPS.

[19]  J. Pearl.  Causality: Models, Reasoning and Inference , 2000 .

[20]  Dan Suciu,et al.  The Complexity of Causality and Responsibility for Query Answers and non-Answers , 2010, Proc. VLDB Endow..

[21]  Ramakrishnan Srikant,et al.  Fast Algorithms for Mining Association Rules in Large Databases , 1994, VLDB.

[22]  Cynthia Rudin,et al.  An Interpretable Model with Globally Consistent Explanations for Credit Risk , 2018, ArXiv.

[23]  Chris Russell,et al.  Counterfactual Explanations Without Opening the Black Box: Automated Decisions and the GDPR , 2017, ArXiv.

[24]  Leopoldo E. Bertossi,et al.  The Shapley Value of Tuples in Query Answering , 2019, ICDT.

[25]  Yair Zick,et al.  Algorithmic Transparency via Quantitative Input Influence: Theory and Experiments with Learning Systems , 2016, 2016 IEEE Symposium on Security and Privacy (SP).

[26]  L. Shapley.  A Value for n-person Games , 1988 .

[27]  Y HalpernJoseph,et al.  Responsibility and blame , 2004 .