Constraint-Driven Explanations of Black-Box ML Models

Aditya Aniruddha Shrotri, Nina Narodytska, Alexey Ignatiev, Joao Marques-Silva, Kuldeep S. Meel, Moshe Vardi

Keywords: Explainability, constraints, uniform sampling

Abstract:

Modern machine learning techniques have enjoyed widespread success, but are plagued by lack of transparency in their decision making, which has led to the emergence of the field of explainable AI. One popular approach called LIME, seeks to explain an opaque model's behavior, by training a surrogate interpretable model to be locally faithful on perturbed instances.
Despite being model-agnostic and easy-to-use, it is known that LIME's explanations can be unstable and are susceptible to adversarial attacks as a result of Out-Of-Distribution (OOD) sampling. Quality of explanations is also calculated heuristically, and lacks a strong theoretical foundation. In spite of numerous attempts to remedy some of these issues, making the LIME framework more trustworthy and reliable remains an open problem.

In this work, we demonstrate that the OOD sampling problem stems from rigidity of the perturbation procedure. To resolve this issue, we propose a theoretically sound framework based on uniform sampling of user-defined subspaces. Through logical constraints, we afford the end-user the flexibility to delineate the precise subspace of the input domain to be explained. This not only helps mitigate the problem of OOD sampling, but also allow experts to drill down and uncover bugs deep inside the model. For testing the quality of generated explanations, we develop an efficient estimation algorithm that is able to certifiably measure the true value of metrics such as fidelity up to any desired degree of accuracy, which can help in building trust in the generated explanations. Our framework called CLIME can be applied to any ML model, and extensive experiments demonstrate its versatility on real-world problems.

One-sentence Summary: Trustworthy and reliable explainations on user-defined constrained subspaces.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=0wagaN9dCy