A Perspective on Explainable Artificial Intelligence Methods: SHAP and LIME
William Harvey Research Institute, NIHR Barts Biomedical Research Centre, Queen Mary University of London（伦敦玛丽女王大学威廉·哈维研究所、NIHR 巴茨生物医学研究中心）；Barts Heart Centre, St Bartholomew’s Hospital, Barts Health NHS Trust（巴茨心脏中心、圣巴塞洛缪医院、巴茨健康 NHS 信托）；Department of Population Health Sciences, University of Leicester（莱斯特大学人口健康科学系）；Department of Computer Science, Faculty of Science, University of Zakho（扎胡大学科学学院计算机科学系）；Department of Engineering for Innovation Medicine, University of Verona（维罗纳大学创新医学工程系）；Health Data Research UK（英国健康数据研究所）；Alan Turing Institute（艾伦·图灵研究所）
Ahmed Salih, Zahra Raisi-Estabragh, Ilaria Boscolo Galazzo, Petia Radeva, Steffen E. Petersen, Gloria Menegaz, Karim Lekadir
可解释人工智能（XAI）方法已经出现，旨在将机器学习（ML）模型的黑箱转化为更易于理解的形式。这些方法有助于传达模型的工作方式，目的是使ML模型更加透明，并提高最终用户对其输出的信任。SHapley Additive exPlanations（SHAP）和Local Interpretable Model Agnostic Explanation（LIME）是两种广泛使用的XAI方法，尤其是在表格数据中。在这篇观点文章中，我们讨论了这两种方法的可解释性指标是如何生成的，并提出了一个解释其输出的框架，突出它们的弱点和优势。具体而言，我们依靠来自生物医学领域的一个案例研究（对患有或不患有心肌梗死的个体进行分类），从模型依赖性和特征之间存在共线性的角度讨论了它们的结果。结果表明，SHAP和LIME高度受所采用的ML模型和特征共线性的影响，这提醒人们在使用和解释它们时需要谨慎。
英文摘要：
eXplainable artificial intelligence (XAI) methods have emerged to convert the black box of machine learning (ML) models into a more digestible form. These methods help to communicate how the model works with the aim of making ML models more transparent and increasing the trust of end-users into their output. SHapley Additive exPlanations (SHAP) and Local Interpretable Model Agnostic Explanation (LIME) are two widely used XAI methods, particularly with tabular data. In this perspective piece, we discuss the way the explainability metrics of these two methods are generated and propose a framework for interpretation of their outputs, highlighting their weaknesses and strengths. Specifically, we discuss their outcomes in terms of model-dependency and in the presence of collinearity among the features, relying on a case study from the biomedical domain (classification of individuals with or without myocardial infarction). The results indicate that SHAP and LIME are highly affected by the adopted ML model and feature collinearity, raising a note of caution on their usage and interpretation.
Predictive process analytics focuses on predicting the future states of running instances of a business process. While advanced machine learning techniques have been used to increase accuracy of predictions, the resulting predictive models lack transparency. Current explainable machine learning methods, such as LIME and SHAP, can be used to interpret black box models. However, it is unclear how fit for purpose these methods are in explaining process predictive models. In this paper, we draw on evaluation measures used in the field of explainable AI and propose functionally-grounded evaluation …
Glaucoma is the second driving reason for partial or complete blindness among all the visual deficiencies which mainly occurs because of excessive pressure in the eye due to anxiety or depression which damages the optic nerve and creates complications in vision. Traditional glaucoma screening is a time-consuming process that necessitates the medical professionals' constant attention, and even so time to time due to the time constrains and pressure they fail to classify correctly that leads to wrong treatment. Numerous efforts have been made to automate the entire glaucoma classification proced…
University of California, Irvine（加州大学欧文分校）；Harvard University（哈佛大学）
As machine learning black boxes are increasingly being deployed in domains such as healthcare and criminal justice, there is growing emphasis on building tools and techniques for explaining these black boxes in an interpretable manner. Such explanations are being leveraged by domain experts to diagnose systematic errors and underlying biases of black boxes. In this paper, we demonstrate that post hoc explanations techniques that rely on input perturbations, such as LIME and SHAP, are not reliable. Specifically, we propose a novel scaffolding technique that effectively hides the biases of any g…
This paper applies eXplainable Artificial Intelligence (XAI) methods to investigate the socioeconomic disparities in COVID patient mortality. An Extreme Gradient Boosting (XGBoost) prediction model is built based on a de-identified Austin area hospital dataset to predict the mortality of COVID-19 patients. We apply two XAI methods, Shapley Additive exPlanations (SHAP) and Locally Interpretable Model Agnostic Explanations (LIME), to compare the global and local interpretation of feature importance. This paper demonstrates the advantages of using XAI which shows the feature importance and decisi…
Explainable AI has attracted much research attention in recent years with feature attribution algorithms, which compute "feature importance" in predictions, becoming increasingly popular. However, there is little analysis of the validity of these algorithms as there is no "ground truth" in the existing datasets to validate their correctness. In this work, we develop a method to quantitatively evaluate the correctness of XAI algorithms by creating datasets with known explanation ground truth. To this end, we focus on the binary classification problems. String datasets are constructed using form…
Which LIME should I trust? Concepts, Challenges, and Solutions
TU Clausthal（克劳斯塔尔工业大学）；University of Mannheim（曼海姆大学）；Ludwig-Maximilians-Universität München（慕尼黑大学）；Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）
Symbiosis Institute of Technology, Symbiosis International (Deemed University)（共生国际（被视为）大学共生技术学院）；Symbiosis Centre for Applied Artificial Intelligence, Symbiosis International (Deemed University)（共生国际（被视为）大学共生应用人工智能中心）；Princess Nourah Bint Abdulrahman University（努拉·宾特·阿卜杜勒拉赫曼公主大学）；Machine Intelligence Research Laboratories（机器智能研究实验室）
In this work, the integration of two machine learning approaches, namely domain adaptation and explainable AI, is proposed to address these two issues of generalized detection and explainability. Firstly the Domain Adversarial Neural Network (DANN) develops a generalized misinformation detector across multiple social media platforms DANN is employed to generate the classification results for test domains with relevant but unseen data. The DANN-based model, a traditional black-box model, cannot justify its outcome, i.e., the labels for the target domain. Hence a Local Interpretable Model-Agnost…
Algorithmic approaches to interpreting machine learning models have proliferated in recent years. We carry out human subject tests that are the first of their kind to isolate the effect of algorithmic explanations on a key aspect of model interpretability, simulatability, while avoiding important confounding experimental factors. A model is simulatable when a person can predict its behavior on new inputs. Through two kinds of simulation tests involving text and tabular data, we evaluate five explanations methods: (1) LIME, (2) Anchor, (3) Decision Boundary, (4) a Prototype model, and (5) a Com…
University of Engineering and Technology（工程技术大学）；Munster Technological University（芒斯特理工大学）；AJOU University（亚洲大学）
Prediction of a machine's Remaining Useful Life (RUL) is one of the key tasks in predictive maintenance. The task is treated as a regression problem where Machine Learning (ML) algorithms are used to predict the RUL of machine components. These ML algorithms are generally used as a black box with a total focus on the performance without identifying the potential causes behind the algorithms' decisions and their working mechanism. We believe, the performance (in terms of Mean Squared Error (MSE), etc.,) alone is not enough to build the trust of the stakeholders in ML prediction rather more insi…
University of Western Australia（西澳大学）；Fiona Stanley Hospital（菲奥娜·斯坦利医院）；Harry Perkins Institute of Medical Research（哈里·珀金斯医学研究所）
Explainable Artificial Intelligence (XAI) has been identified as a viable method for determining the importance of features when making predictions using Machine Learning (ML) models. In this study, we created models that take an individual's health information (e.g. their drug history and comorbidities) as inputs, and predict the probability that the individual will have an Acute Coronary Syndrome (ACS) adverse outcome. Using XAI, we quantified the contribution that specific drugs had on these ACS predictions, thus creating an XAI-based technique for pharmacovigilance monitoring, using ACS as…
Aalto University（阿尔托大学）；KTH Royal Institute of Technology（瑞典皇家理工学院）；Umeå University（于默奥大学）
Machine learning-based systems are rapidly gaining popularity and in-line with that there has been a huge research surge in the field of explainability to ensure that machine learning models are reliable, fair, and can be held liable for their decision-making process. Explainable Artificial Intelligence (XAI) methods are typically deployed to debug black-box machine learning models but in comparison to tabular, text, and image data, explainability in time series is still relatively unexplored. The aim of this study was to achieve and evaluate model agnostic explainability in a time series fore…
University of Liverpool（利物浦大学）；Heriot-Watt University（赫瑞-瓦特大学）；Centrum voor Wiskunde en Informatica（荷兰国家数学与计算机科学研究所）；Delft University of Technology（代尔夫特理工大学）
Given the pressing need for assuring algorithmic transparency, Explainable AI (XAI) has emerged as one of the key areas of AI research. In this paper, we develop a novel Bayesian extension to the LIME framework, one of the most widely used approaches in XAI -- which we call BayLIME. Compared to LIME, BayLIME exploits prior knowledge and Bayesian reasoning to improve both the consistency in repeated explanations of a single prediction and the robustness to kernel settings. BayLIME also exhibits better explanation fidelity than the state-of-the-art (LIME, SHAP and GradCAM) by its ability to inte…
Kalasalingam Academy for Research and Education（卡萨斯林甘研究与教育学院）；GE Corporate Research Center（通用电气企业研究中心）；SINTEF；Norwegian University of Science and Technology（挪威科技大学）；SUNY Polytechnic Institute（纽约州立大学理工学院）
This paper presents an eXplainable Fault Detection and Diagnosis System (XFDDS) for incipient faults in PV panels. The XFDDS is a hybrid approach that combines the model-based and data-driven framework. Model-based FDD for PV panels lacks high fidelity models at low irradiance conditions for detecting incipient faults. To overcome this, a novel irradiance based three diode model (IB3DM) is proposed. It is a nine parameter model that provides higher accuracy even at low irradiance conditions, an important aspect for detecting incipient faults from noise. To exploit PV data, extreme gradient boo…
Cybersecurity is a domain where the data distribution is constantly changing with attackers exploring newer patterns to attack cyber infrastructure. Intrusion detection system is one of the important layers in cyber safety in today's world. Machine learning based network intrusion detection systems started showing effective results in recent years. With deep learning models, detection rates of network intrusion detection system are improved. More accurate the model, more the complexity and hence less the interpretability. Deep neural networks are complex and hard to interpret which makes diffi…
On the Effectiveness of Methods and Metrics for Explainable AI in Remote Sensing Image Scene Classification
Faculty of Electrical Engineering and Computer Science, Technische Universität Berlin（电气工程与计算机科学学院，技术大学柏林）；BIFOLD - Berlin Institute for the Foundations of Learning and Data（柏林学习与数据基础研究院）
German Research Center for Artificial Intelligence (DFKI GmbH)（德国人工智能研究中心 (DFKI GmbH)）；TU Kaiserslautern（凯泽斯劳滕工业大学）
The field of explainable AI (XAI) has quickly become a thriving and prolific community. However, a silent, recurrent and acknowledged issue in this area is the lack of consensus regarding its terminology. In particular, each new contribution seems to rely on its own (and often intuitive) version of terms like "explanation" and "interpretation". Such disarray encumbers the consolidation of advances in the field towards the fulfillment of scientific and regulatory demands e.g., when comparing methods or establishing their compliance with respect to biases and fairness constraints. We propose a t…
Financial Fraud Detection Using Explainable AI and Stacking Ensemble Methods
Computer Science Department, College of Computers and Information Technology, Taif University（计算机科学系，计算机与信息科技学院，泰夫大学）；Department of Computer Science, Taif University（计算机科学系，泰夫大学）
A plethora of recent research has proposed several automated methods based on machine learning (ML) and deep learning (DL) to detect cybersickness in Virtual reality (VR). However, these detection methods are perceived as computationally intensive and black-box methods. Thus, those techniques are neither trustworthy nor practical for deploying on standalone VR head-mounted displays (HMDs). This work presents an explainable artificial intelligence (XAI)-based framework VR-LENS for developing cybersickness detection ML models, explaining them, reducing their size, and deploying them in a Qualcom…
Fraunhofer Institute for Manufacturing Engineering and Automation IPA（弗劳恩霍夫制造工程与自动化研究所）
Not only automation of manufacturing processes but also automation of automation procedures itself become increasingly relevant to automation research. In this context, automated capability assessment, mainly leveraged by deep learning systems driven from 3D CAD data, have been presented. Current assessment systems may be able to assess CAD data with regards to abstract features, e.g. the ability to automatically separate components from bulk goods, or the presence of gripping surfaces. Nevertheless, they suffer from the factor of black box systems, where an assessment can be learned and gener…
In this study, we presented a four-level cross-domain strategy for fake news detection on pre-trained models. Cross-domain text classification is a task of a model adopting a target domain by using the knowledge of the source domain. Explainability is crucial in understanding the behaviour of these complex models. A fine-tune BERT model is used to. perform cross-domain classification with several experiments using datasets from different domains. Explanatory models like Anchor, ELI5, LIME and SHAP are used to design a novel explainable approach to cross-domain levels. The experimental analysis…
Surrogate explainers of black-box machine learning predictions are of paramount importance in the field of eXplainable Artificial Intelligence since they can be applied to any type of data (images, text and tabular), are model-agnostic and are post-hoc (i.e., can be retrofitted). The Local Interpretable Model-agnostic Explanations (LIME) algorithm is often mistakenly unified with a more general framework of surrogate explainers, which may lead to a belief that it is the solution to surrogate explainability. In this paper we empower the community to "build LIME yourself" (bLIMEy) by proposing a…
Local Interpretable Model-Agnostic Explanations (LIME) is a popular method to perform interpretability of any kind of Machine Learning (ML) model. It explains one ML prediction at a time, by learning a simple linear model around the prediction. The model is trained on randomly generated data points, sampled from the training dataset distribution and weighted according to the distance from the reference point - the one being explained by LIME. Feature selection is applied to keep only the most important variables. LIME is widespread across different domains, although its instability - a single …
Fraunhofer IIS/EZRT（弗劳恩霍夫IIS/EZRT）；University of Bamberg（班贝格大学）
End-to-end learning with deep neural networks, such as convolutional neural networks (CNNs), has been demonstrated to be very successful for different tasks of image classification. To make decisions of black-box approaches transparent, different solutions have been proposed. LIME is an approach to explainable AI relying on segmenting images into superpixels based on the Quick-Shift algorithm. In this paper, we present an explorative study of how different superpixel methods, namely Felzenszwalb, SLIC and Compact-Watershed, impact the generated visual explanations. We compare the resulting rel…
Institute of Financial Service Analytics（金融服务分析研究所）；Alfred Lerner College of Business and Economics（阿尔弗雷德·勒纳商业与经济学院）；University Of Delaware（特拉华大学）
This paper examines two different yet related questions related to explainable AI (XAI) practices. Machine learning (ML) is increasingly important in financial services, such as pre-approval, credit underwriting, investments, and various front-end and back-end activities. Machine Learning can automatically detect non-linearities and interactions in training data, facilitating faster and more accurate credit decisions. However, machine learning models are opaque and hard to explain, which are critical elements needed for establishing a reliable technology. The study compares various machine lea…
We discuss promising recent contributions on quantifying feature relevance using Shapley values, where we observed some confusion on which probability distribution is the right one for dropped features. We argue that the confusion is based on not carefully distinguishing between observational and interventional conditional probabilities and try a clarification based on Pearl's seminal work on causality. We conclude that unconditional rather than conditional expectations provide the right notion of dropping features in contradiction to the theoretical justification of the software package SHAP.…
Warsaw University of Technology（华沙理工大学）；University of Warsaw（华沙大学）
Explainable Artificial Intelligence (XAI)has received a great deal of attention recently. Explainability is being presented as a remedy for the distrust of complex and opaque models. Model agnostic methods such as LIME, SHAP, or Break Down promise instance-level interpretability for any complex machine learning model. But how faithful are these additive explanations? Can we rely on additive explanations for non-additive models? In this paper, we (1) examine the behavior of the most popular instance-level explanations under the presence of interactions, (2) introduce a new method that detects i…
