• Corpus ID: 253510293

Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A Review

@inproceedings{Verma2020CounterfactualEA,
  title={Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A Review},
  author={Sahil Verma and Varich Boonsanong and Minh Hoang and Keegan E. Hines and John P. Dickerson and Chirag Shah},
  year={2020}
}
Machine learning plays a role in many deployed decision systems, often in ways that are difficult or impossible to understand by human stakeholders. Explaining, in a human-understandable way, the relationship between the input and output of machine learning models is essential to the development of trustworthy machine learning based systems. A burgeoning body of research seeks to define the goals and methods of explainability in machine learning. In this paper, we seek to review and categorize… 
[PDF] Semantic Reader
16 Citations
Highly Influential Citations
1
Background Citations
6
Methods Citations
2
Results Citations
1

Figures and Tables from this paper

16 Citations

Disagreement amongst counterfactual explanations: How transparency can be deceptive

A large-scale empirical analysis, on 40 datasets, using 12 explanation-generating methods, for two black-box models, yielding over 192.0000 explanations finds alarmingly high disagreement levels between the methods tested.

Even if Explanations: Prior Work, Desiderata & Benchmarks for Semi-Factual XAI

Recently, eXplainable AI (XAI) research has focused on counterfactual explanations as post-hoc justifications for AI-system decisions (e.g. a customer refused a loan might be told: If you asked for a…

Logic for Explainable AI

A comprehensive, semantical and computational theory of explainability along these dimensions which is based on some recent developments in symbolic logic is discussed, particularly applicable to non-symbolic classifiers such as those based on Bayesian networks, decision trees, random forests and some types of neural networks.

Monetizing Explainable AI: A Double-edged Sword

It is argued that monetizing XAI may be a double-edged sword: while monetization may incentivize industry adoption of XAI in a variety of consumer applications, it may also conflict with the original legal and ethical justifications for developing XAI.

Attribution-Scores and Causal Counterfactuals as Explanations in Artificial Intelligence

In this expository article we highlight the relevance of explanations for artificial intelligence, in general, and for the newer developments in {\em explainable AI}, referring to origins and…

Counterfactual Explanation with Missing Values

This paper empirically and theoretically show the risk that missing value imputation methods affect the validity of an action, as well as the features that the action suggests changing, and proposes a new framework of CE, named Counterfactual Explanation by Pairs of Imputation and Action (CEPIA), that enables users to obtain valid actions even with missing values.

counterfactuals: An R Package for Counterfactual Explanation Methods

Thecounterfactuals R package is introduced, which provides a modular and unified R6-based interface for counterfactual explanation methods and proposes some optional methodological extensions to generalize these methods to different scenarios and to make them more comparable.

Supervised Feature Compression based on Counterfactual Analysis

This work aims to leverage Counterfactual Explanations to detect the important decision boundaries of a pre-trained black-box model, which is used to build a supervised discretization of the features in the dataset with a tunable granularity.

Distributionally Robust Recourse Action

The Distributionally Robust Recourse Action (DiRRAc) framework is proposed, which generates a recourse action that has a high probability of being valid under a mixture of model shifts and can be extended to hedge against the misspecification of the mixture weights.

Learning Causal Attributions in Neural Networks: Beyond Direct Effects

This work provides a simple yet effective methodology to capture and maintain direct and indirect causal effects while training an NN model, and proposes effective approximation strategies to quantify causal attributions in high dimensional data.

336 References

Counterfactual Explanations for Machine Learning: A Review

A rubric is designed with desirable properties of counterfactual explanation algorithms and comprehensively evaluate all currently-proposed algorithms against that rubric, providing easy comparison and comprehension of the advantages and disadvantages of different approaches.

Algorithmic Recourse: from Counterfactual Explanations to Interventions

This work relies on causal reasoning to caution against the use of counterfactual explanations as a recommendable set of actions for recourse, and proposes a shift of paradigm from recourse via nearest counterfactUAL explanations to recourse through minimal interventions, shifting the focus from explanations to interventions.

Explaining machine learning classifiers through diverse counterfactual explanations

This work proposes a framework for generating and evaluating a diverse set of counterfactual explanations based on determinantal point processes, and provides metrics that enable comparison ofcounterfactual-based methods to other local explanation methods.

DECE: Decision Explorer with Counterfactual Explanations for Machine Learning Models

DECE, an interactive visualization system that helps understand and explore a model's decisions on individual instances and data subsets, supports exploratory analysis of model decisions by combining the strengths of counterfactual explanations at instance- and subgroup-levels.

Random forest explainability using counterfactual sets

Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanations

DiVE learns a perturbation in a disentangled latent space that is constrained using a diversity-enforcing loss to uncover multiple valuable explanations about the model’s prediction and introduces a mechanism to prevent the model from producing trivial explanations.

CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms

This work presents CARLA (Counterfactual And Recourse LibrAry), a python library for benchmarking counterfactual explanation methods across both different data sets and different machine learning models, providing an extensive benchmark of 11 popular counterfactUAL explanation methods.

ViCE: visual counterfactual explanations for machine learning models

An interactive visual analytics tool that generates counterfactual explanations to contextualize and evaluate model decisions and aims to provide end-users with personalized actionable insights with which to understand, and possibly contest or improve, automated decisions.

Counterfactual Evaluation for Explainable AI

This work proposes a new methodology to evaluate the faithfulness of explanations from thecounterfactual reasoning perspective: the model should produce substantially different outputs for the original input and its corresponding counterfactual edited on a faithful feature.

GeCo: Quality Counterfactual Explanations in Real Time

GeCo is presented, the first system that can compute plausible and feasible counterfactual explanations in real time, and is compared empirically against five other systems described in the literature to show that it is the only systems that can achieve both high quality explanations and real time answers.
...