Inverse Classification for Comparison-based Interpretability in Machine Learning

Laugel, Thibault; Lesot, Marie-Jeanne; Marsala, Christophe; Renard, Xavier; Detyniecki, Marcin

doi:10.48550/arxiv.1712.08443

Cited by 23 publications

(50 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the class of independence-based methods, where the input features of the predictive model are assumed to be independent, some approaches use combinatorial solvers or evolutionary algorithms to generate recourse in the presence of feasibility constraints [57,52,49,23,28,8]. Notable exceptions from this line of work are proposed by [56,32,31,18,15], who use decision trees, random search, support vector machines (SVM) and information networks that are aligned with the recourse objective. Another line of research deploys gradient-based optimization to find low-cost counterfactual explanations in the presence of feasibility and diversity constraints [10,38,39,53,59,46].…”

Section: Counterfactual Explanationsmentioning

confidence: 99%

See 1 more Smart Citation

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

Pawelczyk¹,

Bielawski²,

Heuvel³

et al. 2021

Preprint

View full text Add to dashboard Cite

Counterfactual explanations provide means for prescriptive model explanations by suggesting actionable feature changes (e.g., increase income) that allow individuals to achieve favourable outcomes in the future (e.g., insurance approval). Choosing an appropriate method is a crucial aspect for meaningful counterfactual explanations. As documented in recent reviews, there exists a quickly growing literature with available methods. Yet, in the absence of widely available open-source implementations, the decision in favour of certain models is primarily based on what is readily available. Going forward -to guarantee meaningful comparisons across explanation methods -we present CARLA (Counterfactual And Recourse LibrAry), a python library for benchmarking counterfactual explanation methods across both different data sets and different machine learning models. In summary, our work provides the following contributions: (i) an extensive benchmark of 11 popular counterfactual explanation methods, (ii) a benchmarking framework for research on future counterfactual explanation methods, and (iii) a standardized set of integrated evaluation measures and data sets for transparent and extensive comparisons of these methods. We have open sourced CARLA and our experimental results on Github, making them available as competitive baselines. We welcome contributions from other research groups and practitioners.

show abstract

Section: Counterfactual Explanationsmentioning

confidence: 99%

“…Growing Spheres (GS) (I) Growing Spheres -suggested in [32] -is a random search algorithm, which generates samples around the factual input point until a point with a corresponding counterfactual class label was found. The random samples are generated around x using growing hyperspheres.…”

Section: Face (D)mentioning

confidence: 99%

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

Pawelczyk¹,

Bielawski²,

Heuvel³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Methods based on surrogate explainability approximate ML models using a simple, interpretable model (such as linear regression) [60,75,76]. Contrastive and causal XAI methods explain ML model predictions in terms of minimal interventions or perturbations on input features that change the prediction [11,32,45,55,61,68,89,90,93]. Logic-based methods use tools from logic-based diagnosis that operate on logical representations of ML algorithms [23,40,81] to compute minimal sets of features that are sufficient and necessary for ML model predictions.…”

Section: Related Workmentioning

confidence: 99%

Interpretable Data-Based Explanations for Fairness Debugging

Pradhan¹,

Zhu²,

Glavic³

et al. 2021

Preprint

View full text Add to dashboard Cite

A wide variety of fairness metrics and eXplainable Artificial Intelligence (XAI) approaches have been proposed in the literature to identify bias in machine learning models that are used in critical real-life contexts. However, merely reporting on a model's bias, or generating explanations using existing XAI techniques is insufficient to locate and eventually mitigate sources of bias. In this work, we introduce Gopher, a system that produces compact, interpretable and causal explanations for bias or unexpected model behavior by identifying coherent subsets of the training data that are root-causes for this behavior. Specifically, we introduce the concept of causal responsibility that quantifies the extent to which intervening on training data by removing or updating subsets of it can resolve the bias. Building on this concept, we develop an efficient approach for generating the top-𝑘 patterns that explain model bias that utilizes techniques from the ML community to approximate causal responsibility and uses pruning rules to manage the large search space for patterns. Our experimental evaluation demonstrates the effectiveness of Gopher in generating interpretable explanations for identifying and debugging sources of bias.

show abstract

“…We calculate sparsity using (2), the Gower distance between the test observation and the counterfactual example using (3) and (4) 3 , yN N using Since the categorical features are binarized such that 1 indicates the most common level and 0 otherwise, the L 1 norm between the counterfactual and test observation is identical to the Gower distance. [22] grad opt gradient (2017.12) GS [12] heuristic query (2018.02) CEM [3] FISTA class prob. (2018.09) AR [21] ILP white-box (2019.05) DiCE [14] grad opt gradiet (2019.07) REVISE [8] grad opt gradient (2019.09) FACE [17] graph + heuristic query (2020.06) C-CHVAE [16] grad opt gradient (2020.07) CRUDS [4] grad opt gradient/data (2021.11) MCCE (ours) ctree data/query…”

Section: Real Data Experimentsmentioning

confidence: 99%

“…Some reformulated the problem so that the counterfactual example could be more accurately solved for using an integer program (Ustun et al, 2019). Others searched for the nearest point using random walks (Laugel et al, 2017) or extended the objective function with additional terms so as to handle additional constraints (Mothilal et al, 2020). These more involved objective functions lead to creative uses of optimization tools (e.g., genetic algorithms, Dandl et al, 2020;Rasouli and Yu, 2021).…”

Section: Introductionmentioning

confidence: 99%

MCCE: Monte Carlo sampling of realistic counterfactual explanations

Redelmeier¹,

Jullum²,

Aas³

et al. 2021

Preprint

View full text Add to dashboard Cite

In this paper we introduce MCCE: Monte Carlo sampling of realistic Counterfactual Explanations, a model-based method that generates counterfactual explanations by producing a set of feasible examples using conditional inference trees. Unlike algorithmic-based counterfactual methods that have to solve complex optimization problems or other model based methods that model the data distribution using heavy machine learning models, MCCE is made up of only two light-weight steps (generation and post-processing). MCCE is also straightforward for the end user to understand and implement, handles any type of predictive model and type of feature, takes into account actionability constraints when generating the counterfactual explanations, and generates as many counterfactual explanations as needed. In this paper we introduce MCCE and give a comprehensive list of performance metrics that can be used to compare counterfactual explanations. We also compare MCCE with a range of state-of-the-art methods and a new baseline method on benchmark data sets. MCCE outperforms all model-based methods and most algorithmic-based methods when also taking into account validity (i.e., a correctly changed prediction) and actionability constraints. Finally, we show that MCCE has the strength of performing almost as well when given just a small subset of the training data.

show abstract

Inverse Classification for Comparison-based Interpretability in Machine Learning

Cited by 23 publications

References 0 publications

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

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

Interpretable Data-Based Explanations for Fairness Debugging

MCCE: Monte Carlo sampling of realistic counterfactual explanations

Contact Info

Product

Resources

About