Generating Counterfactual and Contrastive Explanations using SHAP
arXiv:1906.09293
Abstract
With the advent of GDPR, the domain of explainable AI and model interpretability has gained added impetus. Methods to extract and communicate visibility into decision-making models have become legal requirement. Two specific types of explanations, contrastive and counterfactual have been identified as suitable for human understanding. In this paper, we propose a model agnostic method and its systemic implementation to generate these explanations using shapely additive explanations (SHAP). We discuss a generative pipeline to create contrastive explanations and use it to further to generate counterfactual datapoints. This pipeline is tested and discussed on the IRIS, Wine Quality & Mobile Features dataset. Analysis of the results obtained follows.
This work was presented at 2nd Workshop on Humanizing AI (HAI) at IJCAI'19 in Macao, China
References in corpus (3)
Cited by in corpus (11)
- Counterfactual Shapley Additive Explanations
- A survey of algorithmic recourse: definitions, formulations, solutions, and prospects
- Beyond Individualized Recourse: Interpretable and Interactive Summaries of Actionable Recourses
- Counterfactuals and Causability in Explainable Artificial Intelligence: Theory, Algorithms, and Applications
- Evaluating the Correctness of Explainable AI Algorithms for Classification
- Causal Interpretability for Machine Learning -- Problems, Methods and Evaluation
- On the Complexity of SHAP-Score-Based Explanations: Tractability via Knowledge Compilation and Non-Approximability Results
- Algorithmic Recourse in the Wild: Understanding the Impact of Data and Model Shifts
- Towards an Explanation Space to Align Humans and Explainable-AI Teamwork
- SCOUT: Self-aware Discriminant Counterfactual Explanations
- Feature Synergy, Redundancy, and Independence in Global Model Explanations using SHAP Vector Decomposition