CERTIFAI: A Common Framework to Provide Explanations and Analyse the Fairness and Robustness of Black-box Models

By Shubham Sharma, Jette Henderson, Joydeep Ghosh. 2019

192 citations recorded by the source corpus.

Concerns within the machine learning community and external pressures from regulators over the vulnerabilities of machine learning algorithms have spurred on the fields of explainability, robustness, and fairness. Often, issues in explainability, robustness, and fairness are confined to their specific sub-fields and few tools exist for model developers to use to simultaneously build their modeling pipelines in a transparent, accountable, and fair way. This can lead to a bottleneck on the model developer's side as they must juggle multiple methods to evaluate their algorithms. In this paper, we present a single framework for analyzing the robustness, fairness, and explainability of a classifier. The framework, which is based on the generation of counterfactual explanations through a custom genetic algorithm, is flexible, model-agnostic, and does not require access to model internals. The framework allows the user to calculate robustness and fairness scores for individual models and generate explanations for individual predictions which provide a means for actionable recourse (changes to an input to help get a desired outcome). This is the first time that a unified tool has been developed to address three key issues pertaining towards building a responsible artificial intelligence system.

Subfields: Artificial Intelligence, Safety, Robustness & Interpretability, AI Ethics, Fairness & Society

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Safety, Robustness & Interpretability

In AI Ethics, Fairness & Society

Citations in the corpus

On the Fairness of Causal Algorithmic Recourse (2020, background): “…male and female individuals (Ustun, Spangher, and Liu 2019), or comparing the aggregated cost of recourse (burden) across different protected groups (Sharma, Henderson, and Ghosh 2019)— its relation to fairness has only been studied informally, in the sense that differences in recourse have…”
Algorithmic recourse under imperfect causal knowledge: a probabilistic approach (2020, background): “5, (2) where dist(·, ·) is a similarity metric on X , and additional constraints may be added to reflect plausibility, feasibility, or diversity of the obtained counterfactual explanations [19, 20, 32, 33, 39, 44].”
Explainable machine learning in deployment (2019, neutral): “[55] provide details on existing techniques.”
A survey of algorithmic recourse: definitions, formulations, solutions, and prospects (2020, background): “[91, 162, 171, 177], however, Karimi et al.”
Counterfactual Explanations for Machine Learning: A Review (2020, methodology): “factuals (generally diverse by some metric of diversity) for a single input datapoint, therefore they require to be run once per input to get several counterfactuals [26, 47, 57, 64, 82, 85, 95, 98].”
A Survey of Contrastive and Counterfactual Explanation Generation Methods for Explainable Artificial Intelligence (2021, unknown): “…[159], gradient boosted decision trees [147], support vector machines [131], [138], [146], random forests [81], [86], [142]–[144], neural networks [6], [48], [49], [91], [129], [130], [133], [135], [139], [141], [145], [148], [151], or combinations of these [100], [105], [134], [152], [154], [160].”
Multi-Objective Counterfactual Explanations (2020, methodology): “Several model-agnostic counterfactual methods have been proposed [16,9,6,14,23,27,33].”
Current Challenges and Future Opportunities for XAI in Machine Learning-Based Clinical Decision Support Systems: A Systematic Review (2021, methodology): “CLEAR [81] and CERTIFAI [82] are both model-agnostic methods that generate local explanations supported by the provision of counterfactual explanations that show examples of inputs that are generated to be close to the original input but for which the model provides a different outcome.”
Algorithmic Recourse: from Counterfactual Explanations to Interventions (2020, methodology): “While a step in the right direction, this work and others that followed [18, 31, 38, 45] implicitly assume that the set of actions resulting in the desired output would directly follow from the counterfactual explanation.”