Defining Locality for Surrogates in Post-hoc Interpretablity
By Thibault Laugel, Xavier Renard, Marie-Jeanne Lesot, C. Marsala, Marcin Detyniecki. 2018
101 citations recorded by the source corpus.
Local surrogate models, to approximate the local decision boundary of a black-box classifier, constitute one approach to generate explanations for the rationale behind an individual prediction made by the back-box. This paper highlights the importance of defining the right locality, the neighborhood on which a local surrogate is trained, in order to approximate accurately the local black-box decision boundary. Unfortunately, as shown in this paper, this issue is not only a parameter or sampling distribution challenge and has a major impact on the relevance and quality of the approximation of the local black-box decision boundary and thus on the meaning and accuracy of the generated explanation. To overcome the identified problems, quantified with an adapted measure and procedure, we propose to generate surrogate-based explanations for individual predictions based on a sampling centered on particular place of the decision boundary, relevant for the prediction to be explained, rather than on the prediction itself as it is classically done. We evaluate the novel approach compared to state-of-the-art methods and a straightforward improvement thereof on four UCI datasets.
Subfields: Artificial Intelligence
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
- Nadia Burkart
- Marco F. Huber
- Kacper Sokol
- Peter A. Flach
- Ana Marasovic
- Sarah Wiegreffe
- Gesina Schwalbe
- Bettina Finzel
Citations in the corpus
- A Survey on the Explainability of Supervised Machine Learning (2020, background): “Local Surrogate (Laugel et al., 2018) consists of selecting an instance xborder which is close to the nearest black box decision border.”
- Explainability fact sheets: a framework for systematic assessment of explainable approaches (2019, methodology): “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”