Recently, there has been a growing demand for the deployment of Explainable Artificial Intelligence (XAI) algorithms in real-world applications. However, traditional XAI methods typically suffer from a high computational complexity problem, which discourages the deployment of real-time systems to meet the time-demanding requirements of real-world scenarios. Although many approaches have been proposed to improve the efficiency of XAI methods, a comprehensive understanding of the achievements and challenges is still needed. To this end, in this paper we provide a review of efficient XAI. Specifically, we categorize existing techniques of XAI acceleration into efficient non-amortized and efficient amortized methods. The efficient non-amortized methods focus on data-centric or model-centric acceleration upon each individual instance. In contrast, amortized methods focus on learning a unified distribution of model explanations, following the predictive, generative, or reinforcement frameworks, to rapidly derive multiple model explanations. We also analyze the limitations of an efficient XAI pipeline from the perspectives of the training phase, the deployment phase, and the use scenarios. Finally, we summarize the challenges of deploying XAI acceleration methods to real-world scenarios, overcoming the trade-off between faithfulness and efficiency, and the selection of different acceleration methods.
翻译:最近,对在现实世界应用中部署可解释人工智能(XAI)算法的需求日益增长,然而,传统的XAI方法通常会遇到高计算复杂性问题,这不利于部署实时系统,以满足现实世界情景中时间需求的要求,尽管提出了许多方法来提高XAI方法的效率,但仍然需要全面了解成就和挑战。为此,我们在本文件中对高效XAI进行审查。具体地说,我们将XAI加速的现有技术分类为高效的非摊销和高效摊销方法。有效的非摊销方法侧重于每个案例的数据中心或模式中心加速。相比之下,摊销方法侧重于学习统一分配模型解释,遵循预测、归正或强化框架,迅速得出多种模型解释。我们还从培训阶段、部署阶段和使用设想的角度分析XAI高效管道的局限性。最后,我们总结了将XAI加速方法的忠实化方法与现实世界加速度选择方法之间的困难。