Abstract
The main objective of eXplainable Artificial Intelligence (XAI) is to provide effective explanations for black-box classifiers. The existing literature lists many desirable properties for explanations to be useful, but there is a scarce consensus on how to quantitatively evaluate explanations in practice. Moreover, explanations are typically used only to inspect black-box models, and the proactive use of explanations as a decision support is generally overlooked. Among the many approaches to XAI, a widely adopted paradigm is Local Linear Explanations—with LIME and SHAP emerging as state-of-the-art methods. We show that these methods are plagued by many defects including unstable explanations, divergence of actual implementations from the promised theoretical properties, and explanations for the wrong label. This highlights the need to have standard and unbiased evaluation procedures for Local Linear Explanations in the XAI field. In this paper we address the problem of identifying a clear and unambiguous set of metrics for the evaluation of Local Linear Explanations. This set includes both existing and novel metrics defined specifically for this class of explanations. All metrics have been included in an open Python framework, named LEAF. The purpose of LEAF is to provide a reference for end users to evaluate explanations in a standardised and unbiased way, and to guide researchers towards developing improved explainable techniques.
Highlights
IntroductionThe field of Machine Learning (ML) has experienced a surge in practical applications
In recent years, the field of Machine Learning (ML) has experienced a surge in practical applications
In this paper we focus on the class of explanation models named local linear explanations (LLE)
Summary
The field of Machine Learning (ML) has experienced a surge in practical applications. Many ML models, spanning from random forests to deep neural networks, do not provide a human-understandable clarification of their internal decision processes: this issue is known as the black-box problem (Burrell, 2016). Several model-specific and data-specific explanation models have been developed, e.g., for deep neural networks (Binder et al, 2016; Selvaraju et al, 2019), deep relational machines (Srinivasan et al, 2019), time series (Karlsson et al, 2019), multi-labelled and ontology-linked data (Panigutti et al., 2020b) or logic problems (Biecek, 2018); software toolkits including the implementation of various XAI algorithms have been introduced (Arya et al, 2019). A comprehensive survey of explainability methods can be found in Guidotti et al (2018) and in Dosilovicet al. (2018)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have