Towards Quantification of Explainability in Explainable Artificial Intelligence Methods
arXiv:1911.10104
Abstract
Artificial Intelligence (AI) has become an integral part of domains such as security, finance, healthcare, medicine, and criminal justice. Explaining the decisions of AI systems in human terms is a key challenge--due to the high complexity of the model, as well as the potential implications on human interests, rights, and lives . While Explainable AI is an emerging field of research, there is no consensus on the definition, quantification, and formalization of explainability. In fact, the quantification of explainability is an open challenge. In our previous work, we incorporated domain knowledge for better explainability, however, we were unable to quantify the extent of explainability. In this work, we (1) briefly analyze the definitions of explainability from the perspective of different disciplines (e.g., psychology, social science), properties of explanation, explanation methods, and human-friendly explanations; and (2) propose and formulate an approach to quantify the extent of explainability. Our experimental result suggests a reasonable and model-agnostic way to quantify explainability
Submitted to FLAIRS-33
References in corpus (5)
- Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)
- Quantifying Model Complexity via Functional Decomposition for Better Post-Hoc Interpretability
- Assessing the Local Interpretability of Machine Learning Models
- Infusing domain knowledge in AI-based "black box" models for better explainability with application in bankruptcy prediction
- TIP: Typifying the Interpretability of Procedures