In recent years, a large number of XAI (eXplainable Artificial Intelligence) solutions have been proposed to explain existing ML (Machine Learning) models or to create interpretable ML models. Evaluation measures have recently been proposed and it is now possible to compare these XAI solutions. However, selecting the most relevant XAI solution among all this diversity is still a tedious task, especially when meeting specific needs and constraints. In this paper, we propose AutoXAI, a framework that recommends the best XAI solution and its hyperparameters according to specific XAI evaluation metrics while considering the user's context (dataset, ML model, XAI needs and constraints). It adapts approaches from context-aware recommender systems and strategies of optimization and evaluation from AutoML (Automated Machine Learning). We apply AutoXAI to two use cases, and show that it recommends XAI solutions adapted to the user's needs with the best hyperparameters matching the user's constraints.
翻译:近年来,提出了大量XAI(可移植人工智能)解决方案,以解释现有的ML(Machine Learning)模式或创建可解释的ML模式。最近提出了评估措施,现在可以比较这些XAI解决方案。然而,在所有这种多样性中选择最相关的XAI解决方案仍是一项乏味的任务,特别是在满足具体需要和限制时。在本文件中,我们提出了AutoXAI,这是一个根据特定的XAI评价指标(数据集、ML模型、XAI需要和限制)推荐最佳XAI解决方案及其超参数的框架,同时考虑用户的上下文(数据集、ML模型、XAI需要和限制),它从符合环境的推荐系统以及来自自动移动(自动机学习)的优化和评价战略(自动机学习)中调整各种做法。我们应用AutoXAI来使用两个案例,并表明它建议采用符合用户需求的最佳的XAI解决方案与符合用户制约的最佳超参数。