Defining Locality for Surrogates in Post-hoc Interpretablity

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

doi:10.48550/arxiv.1806.07498

Cited by 9 publications

(19 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, model-agnostic explainers can render some desiderata difficult to achieve since these approaches cannot take advantage of model-specific aspects of predictive algorithms. LIME [44] has recently been subjected to studies aiming to validate its usability [31,50,57], which discovered lack of stability for its explanations (S3) and shortcomings of their locality (U1), hence raising questions about the validation methods (V2) used to evaluate this technique in the first place. We concur that had a list of requirements such as one presented in this paper been available, some of these issues could have been avoided.…”

Section: Discussionmentioning

confidence: 99%

Explainability fact sheets

Sokol

Flach

2020

Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency

167

View full text Add to dashboard Cite

Explanations in Machine Learning come in many forms, but a consensus regarding their desired properties is yet to emerge. In this paper we introduce a taxonomy and a set of descriptors that can be used to characterise and systematically assess explainable systems along five key dimensions: functional, operational, usability, safety and validation. In order to design a comprehensive and representative taxonomy and associated descriptors we surveyed the eXplainable Artificial Intelligence literature, extracting the criteria and desiderata that other authors have proposed or implicitly used in their research. The survey includes papers introducing new explainability algorithms to see what criteria are used to guide their development and how these algorithms are evaluated, as well as papers proposing such criteria from both computer science and social science perspectives. This novel framework allows to systematically compare and contrast explainability approaches, not just to better understand their capabilities but also to identify discrepancies between their theoretical qualities and properties of their implementations. We developed an operationalisation of the framework in the form of Explainability Fact Sheets, which enable researchers and practitioners alike to quickly grasp capabilities and limitations of a particular explainable method. When used as a Work Sheet, our taxonomy can guide the development of new explainability approaches by aiding in their critical evaluation along the five proposed dimensions.

show abstract

Section: Discussionmentioning

confidence: 99%

Explainability fact sheets

Sokol

Flach

2020

Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency

167

View full text Add to dashboard Cite

show abstract

“…Microsoft's Interpret and Oracle's Skater, for example, mainly serve as wrappers for a wide range of explainability packages, hence risking users' trust as they are prone to errors introduce therein. LIME [27], which is part of both these packages, has recently been shown to have issues with locality of its explanations [22], which affects both Interpret and Skater. Therefore, in a long term we want to re-implement necessary algorithms from the grounds up, which should be possible given the common functional base of the package.…”

Section: Discussionmentioning

confidence: 99%

FAT Forensics: A Python Toolbox for Algorithmic Fairness, Accountability and Transparency

Sokol,

Santos-Rodriguez,

Flach

2019

Preprint

View full text Add to dashboard Cite

Machine learning algorithms can take important decisions, sometimes legally binding, about our everyday life. In most cases, however, these systems and decisions are neither regulated nor certified. Given the potential harm that these algorithms can cause, qualities such as fairness, accountability and transparency of predictive systems are of paramount importance. Recent literature suggested voluntary self-reporting on these aspects of predictive systemse.g., data sheets for data sets -but their scope is often limited to a single component of a machine learning pipeline, and producing them requires manual labour. To resolve this impasse and ensure high-quality, fair, transparent and reliable machine learning systems, we developed an open source toolbox that can inspect selected fairness, accountability and transparency aspects of these systems to automatically and objectively report them back to their engineers and users. We describe design, scope and usage examples of this Python toolbox in this paper. The toolbox provides functionality for inspecting fairness, accountability and transparency of all aspects of the machine learning process: data (and their features), models and predictions. It is available to the public under the BSD 3-Clause open source licence.

show abstract

“…Laugel. et al [8] suggested to test the performance of fz on the test instances that fall into a hypersphere with a fixed radius and z as center. Having a fixed radius has a disadvantage that the sphere may include only instances of the same class.…”

Section: Quantitative Evaluationmentioning

confidence: 99%

“…The parameter σ of the proximity kernel plays an important role: a fixed σ can lead to neighbourhoods that do not include a decision boundary, or that include a too big part of the decision boundary which cannot be approximated linearly. Laugel et al [8] spotted this problem and suggested to sample instances close to the nearest decision boundary to z within a fixed hyper-sphere. However, the fixed hypersphere can also lead to too small or too big neighbourhoods.…”

Section: Introductionmentioning

confidence: 99%

LEAFAGE: Example-based and Feature importance-based Explanations for Black-box ML models

Adhikari

Tax

Satta

et al. 2019

2019 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)

View full text Add to dashboard Cite

Explainable Artificial Intelligence (XAI) is an emergent research field which tries to cope with the lack of transparency of AI systems, by providing human understandable explanations for the underlying Machine Learning models. This work presents a new explanation extraction method called LEAFAGE. Explanations are provided both in terms of feature importance and of similar classification examples. The latter is a well known strategy for problem solving and justification in social science. LEAFAGE leverages on the fact that the reasoning behind a single decision/prediction for a single data point is generally simpler to understand than the complete model; it produces explanations by generating simpler yet locally accurate approximations of the original model. LEAFAGE performs overall better than the current state of the art in terms of fidelity of the model approximation, in particular when Machine Learning models with non-linear decision boundaries are analysed. LEAFAGE was also tested in terms of usefulness for the user, an aspect still largely overlooked in the scientific literature. Results show interesting and partly counter-intuitive findings, such as the fact that providing no explanation is sometimes better than providing certain kinds of explanation.

show abstract

Defining Locality for Surrogates in Post-hoc Interpretablity

Cited by 9 publications

References 0 publications

Explainability fact sheets

Explainability fact sheets

FAT Forensics: A Python Toolbox for Algorithmic Fairness, Accountability and Transparency

LEAFAGE: Example-based and Feature importance-based Explanations for Black-box ML models

Contact Info

Product

Resources

About