In many practical applications, deep neural networks have been typically deployed to operate as a black box predictor. Despite the high amount of work on interpretability and high demand on the reliability of these systems, they typically still have to include a human actor in the loop, to validate the decisions and handle unpredictable failures and unexpected corner cases. This is true in particular for failure-critical application domains, such as medical diagnosis. We present a novel approach to explain and support an interpretation of the decision-making process to a human expert operating a deep learning system based on Convolutional Neural Network (CNN). By modeling activation statistics on selected layers of a trained CNN via Gaussian Mixture Models (GMM), we develop a novel perceptual code in binary vector space that describes how the input sample is processed by the CNN. By measuring distances between pairs of samples in this perceptual encoding space, for any new input sample, we can now retrieve a set of most perceptually similar and dissimilar samples from an existing atlas of labeled samples, to support and clarify the decision made by the CNN model. Possible uses of this approach include for example Computer-Aided Diagnosis (CAD) systems working with medical imaging data, such as Magnetic Resonance Imaging (MRI) or Computed Tomography (CT) scans. We demonstrate the viability of our method in the domain of medical imaging for patient condition diagnosis, as the proposed decision explanation method via similar ground truth domain examples (e.g. from existing diagnosis archives) will be interpretable by the operating medical personnel. Our results indicate that our method is capable of detecting distinct prediction strategies that enable us to identify the most similar predictions from an existing atlas.
Clinical decision support using deep neural networks has become a topic of steadily growing interest. While recent work has repeatedly demonstrated that deep learning offers major advantages for medical image classification over traditional methods, clinicians are often hesitant to adopt the technology because its underlying decision-making process is considered to be intransparent and difficult to comprehend. In recent years, this has been addressed by a variety of approaches that have successfully contributed to providing deeper insight. Most notably, additive feature attribution methods are…
Explaining Digital Pathology Models via Clustering Activations
Faculty of Informatics, Masaryk University, Brno, Czech Republic（马萨里克大学信息学院，布拉格，捷克共和国）；Institute of Computer Science, Masaryk University, Brno, Czech Republic（马萨里克大学计算机科学研究所，布拉格，捷克共和国）；Masaryk Memorial Cancer Institute, Brno, Czech Republic（马萨里克纪念癌症研究所，布拉格，捷克共和国）
Hochschule Pforzheim（普福尔茨海姆应用技术大学）；Smart Data and Knowledge Services German Research Center for Artificial Intelligence GmbH (DFKI)（德国人工智能研究中心智能数据与知识服务部）；Technische Universität Kaiserslautern（凯泽斯劳滕工业大学）；Universitätsklinikum Münster（明斯特大学医院）；Universitätsklinikum Düsseldorf（杜塞尔多夫大学医院）；National University of Science and Technology (NUST)（巴基斯坦国立科技大学）；National Center of Artificial Intelligence（国家人工智能中心）
Deep learning based medical image classifiers have shown remarkable prowess in various application areas like ophthalmology, dermatology, pathology, and radiology. However, the acceptance of these Computer-Aided Diagnosis (CAD) systems in real clinical setups is severely limited primarily because their decision-making process remains largely obscure. This work aims at elucidating a deep learning based medical image classifier by verifying that the model learns and utilizes similar disease-related concepts as described and employed by dermatologists. We used a well-trained and high performing n…
University of Pittsburgh（匹兹堡大学）；Carnegie Mellon University（卡内基梅隆大学）；University of Pittsburgh Medical School（匹兹堡大学医学院）
We propose a BlackBox Counterfactual Explainer, designed to explain image classification models for medical applications. Classical approaches (e.g., saliency maps) that assess feature importance do not explain "how" imaging features in important anatomical regions are relevant to the classification decision. Our framework explains the decision for a target class by gradually "exaggerating" the semantic effect of the class in a query image. We adopted a Generative Adversarial Network (GAN) to generate a progressive set of perturbations to a query image, such that the classification decision ch…
We propose an approach for explaining Bayesian network classifiers, which is based on compiling such classifiers into decision functions that have a tractable and symbolic form. We introduce two types of explanations for why a classifier may have classified an instance positively or negatively and suggest algorithms for computing these explanations. The first type of explanation identifies a minimal set of the currently active features that is responsible for the current classification, while the second type of explanation identifies a minimal set of features whose current state (active or not…
While machine learning models are usually assumed to always output a prediction, there also exist extensions in the form of reject options which allow the model to reject inputs where only a prediction with an unacceptably low certainty would be possible. With the ongoing rise of eXplainable AI, a lot of methods for explaining model predictions have been developed. However, understanding why a given input was rejected, instead of being classified by the model, is also of interest. Surprisingly, explanations of rejects have not been considered so far. We propose to use counterfactual explanatio…
UC San Diego（加州大学圣地亚哥分校）；Stanford University（斯坦福大学）
Despite their high accuracies, modern complex image classifiers cannot be trusted for sensitive tasks due to their unknown decision-making process and potential biases. Counterfactual explanations are very effective in providing transparency for these black-box algorithms. Nevertheless, generating counterfactuals that can have a consistent impact on classifier outputs and yet expose interpretable feature changes is a very challenging task. We introduce a novel method to generate causal and yet interpretable counterfactual explanations for image classifiers using pretrained generative models wi…
Despite widespread adoption, machine learning models remain mostly black boxes. Understanding the reasons behind predictions is, however, quite important in assessing trust, which is fundamental if one plans to take action based on a prediction, or when choosing whether to deploy a new model. Such understanding also provides insights into the model, which can be used to transform an untrustworthy model or prediction into a trustworthy one. In this work, we propose LIME, a novel explanation technique that explains the predictions of any classifier in an interpretable and faithful manner, by lea…
IRIT-CNRS（图卢兹计算机科学研究所-法国国家科学研究中心）；University of Toulouse（图卢兹大学）；CIRSFID（法律史、哲学与社会学研究中心）；University of Bologna（博洛尼亚大学）
This paper brings together two lines of research: factor-based models of case-based reasoning (CBR) and the logical specification of classifiers. Logical approaches to classifiers capture the connection between features and outcomes in classifier systems. Factor-based reasoning is a popular approach to reasoning by precedent in AI & Law. Horty (2011) has developed the factor-based models of precedent into a theory of precedential constraint. In this paper we combine the modal logic approach (binary-input classifier, BLC) to classifiers and their explanations given by Liu & Lorini (2021) with H…
The paper introduces a novel framework for extracting model-agnostic human interpretable rules to explain a classifier's output. The human interpretable rule is defined as an axis-aligned hyper-cuboid containing the instance for which the classification decision has to be explained. The proposed procedure finds the largest (high \textit{coverage}) axis-aligned hyper-cuboid such that a high percentage of the instances in the hyper-cuboid have the same class label as the instance being explained (high \textit{precision}). Novel approximations to the coverage and precision measures in terms of th…
University of Toulouse（图卢兹大学）；Monash University（莫纳什大学）；IRIT（图卢兹信息学研究所）；CNRS（法国国家科学研究中心）
Recent work has shown that not only decision trees (DTs) may not be interpretable but also proposed a polynomial-time algorithm for computing one PI-explanation of a DT. This paper shows that for a wide range of classifiers, globally referred to as decision graphs, and which include decision trees and binary decision diagrams, but also their multi-valued variants, there exist polynomial-time algorithms for computing one PI-explanation. In addition, the paper also proposes a polynomial-time algorithm for computing one contrastive explanation. These novel algorithms build on explanation graphs (…
Queen’s University Belfast（贝尔法斯特女王大学）；King’s College London（伦敦国王学院）；University of Liverpool（利物浦大学）；University of Oxford（牛津大学）
The black-box nature of deep neural networks (DNNs) makes it impossible to understand why a particular output is produced, creating demand for "Explainable AI". In this paper, we show that statistical fault localization (SFL) techniques from software engineering deliver high quality explanations of the outputs of DNNs, where we define an explanation as a minimal subset of features sufficient for making the same decision as for the original input. We present an algorithm and a tool called DeepCover, which synthesizes a ranking of the features of the inputs using SFL and constructs explanations …
Institute for Artificial Intelligence and Decision Support（人工智能与决策支持研究所）；Medical University of Vienna（维也纳医科大学）
Deep neural networks and other intricate Artificial Intelligence (AI) models have reached high levels of accuracy on many biomedical natural language processing tasks. However, their applicability in real-world use cases may be limited due to their vague inner working and decision logic. A post-hoc explanation method can approximate the behavior of a black-box AI model by extracting relationships between feature values and outcomes. In this paper, we introduce a post-hoc explanation method that utilizes confident itemsets to approximate the behavior of black-box classifiers for medical informa…
Universität Augsburg（奥格斯堡大学）；Xitaso GmbH（Xitaso有限公司）
In socio-technical settings, operators are increasingly assisted by decision support systems. By employing these, important properties of socio-technical systems such as self-adaptation and self-optimization are expected to improve further. To be accepted by and engage efficiently with operators, decision support systems need to be able to provide explanations regarding the reasoning behind specific decisions. In this paper, we propose the usage of Learning Classifier Systems, a family of rule-based machine learning methods, to facilitate transparent decision making and highlight some techniqu…
University of Campinas（坎皮纳斯大学）；Leeds University Business School（利兹大学商学院）；COMSATS University Islamabad（伊斯兰堡COMSATS大学）
The use of algorithm-agnostic approaches is an emerging area of research for explaining the contribution of individual features towards the predicted outcome. Whilst there is a focus on explaining the prediction itself, a little has been done on explaining the robustness of these models, that is, how each feature contributes towards achieving that robustness. In this paper, we propose the use of Shapley values to explain the contribution of each feature towards the model's robustness, measured in terms of Receiver-operating Characteristics (ROC) curve and the Area under the ROC curve (AUC). Wi…
In the real world, RL agents should be rewarded for fulfilling human preferences. We show that RL agents implicitly learn the preferences of humans in their environment. Training a classifier to predict if a simulated human's preferences are fulfilled based on the activations of a RL agent's neural network gets .93 AUC. Training a classifier on the raw environment state gets only .8 AUC. Training the classifier off of the RL agent's activations also does much better than training off of activations from an autoencoder. The human preference classifier can be used as the reward function of an RL…
University of Toulouse（图卢兹大学）；IRIT, CNRS（法国国家科学研究中心图卢兹计算机科学研究所）
Despite the progress observed with model-agnostic explainable AI (XAI), it is the case that model-agnostic XAI can produce incorrect explanations. One alternative are the so-called formal approaches to XAI, that include PI-explanations. Unfortunately, PI-explanations also exhibit important drawbacks, the most visible of which is arguably their size. The computation of relevant features serves to trade off probabilistic precision for the number of features in an explanation. However, even for very simple classifiers, the complexity of computing sets of relevant features is prohibitive. This pap…
Lenovo Research（联想研究院）；University of Chinese Academy of Sciences（中国科学院大学）
Despite outstanding contribution to the significant progress of Artificial Intelligence (AI), deep learning models remain mostly black boxes, which are extremely weak in explainability of the reasoning process and prediction results. Explainability is not only a gateway between AI and society but also a powerful tool to detect flaws in the model and biases in the data. Local Interpretable Model-agnostic Explanation (LIME) is a recent approach that uses an interpretable model to form a local explanation for the individual prediction result. The current implementation of LIME adopts the linear r…
University College Dublin（都柏林大学学院）；Insight Centre for Data Analytics, UCD（UCD洞察数据分析中心）；ML Labs, SFI CRT（SFI CRT机器学习实验室）
Very few eXplainable AI (XAI) studies consider how users understanding of explanations might change depending on whether they know more or less about the to be explained domain (i.e., whether they differ in their expertise). Yet, expertise is a critical facet of most high stakes, human decision making (e.g., understanding how a trainee doctor differs from an experienced consultant). Accordingly, this paper reports a novel, user study (N=96) on how peoples expertise in a domain affects their understanding of post-hoc explanations by example for a deep-learning, black box classifier. The results…
Random Forest (RFs) are among the most widely used Machine Learning (ML) classifiers. Even though RFs are not interpretable, there are no dedicated non-heuristic approaches for computing explanations of RFs. Moreover, there is recent work on polynomial algorithms for explaining ML models, including naive Bayes classifiers. Hence, one question is whether finding explanations of RFs can be solved in polynomial time. This paper answers this question negatively, by proving that computing one PI-explanation of an RF is D^P-complete. Furthermore, the paper proposes a propositional encoding for compu…
Explaining Time Series Classifiers with PHAR: Rule Extraction and Fusion from Post-hoc Attributions
Jagiellonian Human-Centered AI Lab, Mark Kac Center for Complex Systems Research（杰克利昂人类中心人工智能实验室、马克·卡复杂系统研究中心）；Institute of Applied Computer Science, Jagiellonian University（应用计算机科学研究所、杰克利昂大学）
TU Kaiserslautern（凯泽斯劳滕工业大学）；German Research Center for Artificial Intelligence GmbH (DFKI)（德国人工智能研究中心）
Human-centric explainability of AI-based Decision Support Systems (DSS) using visual input modalities is directly related to reliability and practicality of such algorithms. An otherwise accurate and robust DSS might not enjoy trust of experts in critical application areas if it is not able to provide reasonable justification of its predictions. This paper introduces Concept Localization Maps (CLMs), which is a novel approach towards explainable image classifiers employed as DSS. CLMs extend Concept Activation Vectors (CAVs) by locating significant regions corresponding to a learned concept in…
Deep neural networks are complex and opaque. As they enter application in a variety of important and safety critical domains, users seek methods to explain their output predictions. We develop an approach to explaining deep neural networks by constructing causal models on salient concepts contained in a CNN. We develop methods to extract salient concepts throughout a target network by using autoencoders trained to extract human-understandable representations of network activations. We then build a bayesian causal model using these extracted concepts as variables in order to explain image class…
