New applications of Explainable artificial intelligence part2(Machine Learning 2023)
- A novel approach to generate datasets with XAI ground truth to evaluate image models(arXiv)
Author : Miquel Miró-Nicolau, Antoni Jaume-i-Capó, Gabriel Moyà-Alcover
Abstract : With the increased usage of artificial intelligence (AI), it is imperative to understand how these models work internally. These needs have led to the development of a new field called eXplainable artificial intelligence (XAI). This field consists of on a set of techniques that allows us to theoretically determine the cause of the AI decisions. One unsolved question about XAI is how to measure the quality of explanations. In this study, we propose a new method to generate datasets with ground truth (GT). These datasets allow us to measure how faithful is a method without ad hoc solutions. We conducted a set of experiments that compared our GT with real model explanations and obtained excellent results confirming that our proposed method is correct.
2.Efficient XAI Techniques: A Taxonomic Survey (arXiv)
Author : Yu-Neng Chuang, Guanchu Wang, Fan Yang, Zirui Liu, Xuanting Cai, Mengnan Du, Xia Hu
Abstract : 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.
