A Survey on the Explainability of Supervised Machine Learning
Fraunhofer Institute for Optronics, System Technologies, and Image Exploitation IOSB（弗劳恩霍夫光电、系统技术与图像利用研究所IOSB）；University of Stuttgart（斯图加特大学）；Fraunhofer Institute for Manufacturing Engineering and Automation IPA（弗劳恩霍夫制造工程与自动化研究所IPA）
Nadia Burkart, Marco F. Huber
备注：
Accepted for publication at the Journal of Artificial Intelligence Research (JAIR)
发表信息：
Journal of Artificial Intelligence Research (JAIR), 70:245-317, 2021
Predictions obtained by, e.g., artificial neural networks have a high accuracy but humans often perceive the models as black boxes. Insights about the decision making are mostly opaque for humans. Particularly understanding the decision making in highly sensitive areas such as healthcare or fifinance, is of paramount importance. The decision-making behind the black boxes requires it to be more transparent, accountable, and understandable for humans. This survey paper provides essential definitions, an overview of the different principles and methodologies of explainable Supervised Machine Learning (SML). We conduct a state-of-the-art survey that reviews past and recent explainable SML approaches and classifies them according to the introduced definitions. Finally, we illustrate principles by means of an explanatory case study and discuss important future directions.
Graph neural networks (GNNs) have been extensively developed for graph representation learning in various application domains. However, similar to all other neural networks models, GNNs suffer from the black-box problem as people cannot understand the mechanism underlying them. To solve this problem, several GNN explainability methods have been proposed to explain the decisions made by GNNs. In this survey, we give an overview of the state-of-the-art GNN explainability methods and how they are evaluated. Furthermore, we propose a new evaluation metric and conduct thorough experiments to compar…
In ML-aided decision-making tasks, such as fraud detection or medical diagnosis, the human-in-the-loop, usually a domain-expert without technical ML knowledge, prefers high-level concept-based explanations instead of low-level explanations based on model features. To obtain faithful concept-based explanations, we leverage multi-task learning to train a neural network that jointly learns to predict a decision task based on the predictions of a precedent explainability task (i.e., multi-label concepts). There are two main challenges to overcome: concept label scarcity and the joint learning. To …
Deep learning methods are achieving ever-increasing performance on many artificial intelligence tasks. A major limitation of deep models is that they are not amenable to interpretability. This limitation can be circumvented by developing post hoc techniques to explain the predictions, giving rise to the area of explainability. Recently, explainability of deep models on images and texts has achieved significant progress. In the area of graph data, graph neural networks (GNNs) and their explainability are experiencing rapid developments. However, there is neither a unified treatment of GNN expla…
A Survey on Explainability of Graph Neural Networks
University of Illinois Chicago（伊利诺伊大学芝加哥分校）；Georgia Institute of Technology（佐治亚理工学院）；IBM T. J. Watson Research Center（IBM托马斯·J·沃森研究中心）；University of Illinois, Chicago（伊利诺伊大学芝加哥分校）
Artificial intelligence (AI) has huge potential to improve the health and well-being of people, but adoption in clinical practice is still limited. Lack of transparency is identified as one of the main barriers to implementation, as clinicians should be confident the AI system can be trusted. Explainable AI has the potential to overcome this issue and can be a step towards trustworthy AI. In this paper we review the recent literature to provide guidance to researchers and practitioners on the design of explainable AI systems for the health-care domain and contribute to formalization of the fie…
Artificial Intelligence (AI) increasingly shows its potential to outperform predicate logic algorithms and human control alike. In automatically deriving a system model, AI algorithms learn relations in data that are not detectable for humans. This great strength, however, also makes use of AI methods dubious. The more complex a model, the more difficult it is for a human to understand the reasoning for the decisions. As currently, fully automated AI algorithms are sparse, every algorithm has to provide a reasoning for human operators. For data engineers, metrics such as accuracy and sensitivi…
Every year physicians face an increasing demand of image-based diagnosis from patients, a problem that can be addressed with recent artificial intelligence methods. In this context, we survey works in the area of automatic report generation from medical images, with emphasis on methods using deep neural networks, with respect to: (1) Datasets, (2) Architecture Design, (3) Explainability and (4) Evaluation Metrics. Our survey identifies interesting developments, but also remaining challenges. Among them, the current evaluation of generated reports is especially weak, since it mostly relies on t…
As the applications of Natural Language Processing (NLP) in sensitive areas like Political Profiling, Review of Essays in Education, etc. proliferate, there is a great need for increasing transparency in NLP models to build trust with stakeholders and identify biases. A lot of work in Explainable AI has aimed to devise explanation methods that give humans insights into the workings and predictions of NLP models. While these methods distill predictions from complex models like Neural Networks into consumable explanations, how humans understand these explanations is still widely unexplored. Inna…
Tencent AI Lab（腾讯人工智能实验室）；Sun Yat-sen University（中山大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Zhejiang University（浙江大学）；University of Texas at Arlington（德克萨斯大学阿灵顿分校）；Shenzhen Research Institute of Big Data（深圳大数据研究院）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Peking University（北京大学）；Tsinghua University（清华大学）；Zhejiang Lab（之江实验室）
Deep graph learning has achieved remarkable progresses in both business and scientific areas ranging from finance and e-commerce, to drug and advanced material discovery. Despite these progresses, how to ensure various deep graph learning algorithms behave in a socially responsible manner and meet regulatory compliance requirements becomes an emerging problem, especially in risk-sensitive domains. Trustworthy graph learning (TwGL) aims to solve the above problems from a technical viewpoint. In contrast to conventional graph learning research which mainly cares about model performance, TwGL con…
This survey reviews explainability methods for vision-based self-driving systems trained with behavior cloning. The concept of explainability has several facets and the need for explainability is strong in driving, a safety-critical application. Gathering contributions from several research fields, namely computer vision, deep learning, autonomous driving, explainable AI (X-AI), this survey tackles several points. First, it discusses definitions, context, and motivation for gaining more interpretability and explainability from self-driving systems, as well as the challenges that are specific t…
While state-of-the-art NLP explainability (XAI) methods focus on explaining per-sample decisions in supervised end or probing tasks, this is insufficient to explain and quantify model knowledge transfer during (un-)supervised training. Thus, for TX-Ray, we modify the established computer vision explainability principle of 'visualizing preferred inputs of neurons' to make it usable transfer analysis and NLP. This allows one to analyze, track and quantify how self- or supervised NLP models first build knowledge abstractions in pretraining (1), and then transfer these abstractions to a new domain…
Bayer AG（拜耳股份公司）；Median Technologies（Median科技公司）；Bayer Crop Science（拜耳作物科学公司）；Pfizer Worldwide Research Development and Medical（辉瑞全球研发与医疗部门）
In pre-clinical pathology, there is a paradox between the abundance of raw data (whole slide images from many organs of many individual animals) and the lack of pixel-level slide annotations done by pathologists. Due to time constraints and requirements from regulatory authorities, diagnoses are instead stored as slide labels. Weakly supervised training is designed to take advantage of those data, and the trained models can be used by pathologists to rank slides by their probability of containing a given lesion of interest. In this work, we propose a novel contextualized eXplainable AI (XAI) f…
Explainability for Large Language Models: A Survey
New Jersey Institute of Technology（新泽西理工学院）；Johns Hopkins University（约翰斯·霍普金斯大学）；Wake Forest University（维克森林大学）；University of Georgia（佐治亚大学）；Shanghai Jiao Tong University（上海交通大学）；Institute of Computing Technology, CAS（中国科学院计算技术研究所）；Baidu Inc.（百度公司）；Rice University（莱斯大学）
University of Cambridge（剑桥大学）；University of California Los Angeles（加州大学洛杉矶分校）；The Alan Turing Institute（艾伦·图灵研究所）
Unsupervised black-box models are challenging to interpret. Indeed, most existing explainability methods require labels to select which component(s) of the black-box's output to interpret. In the absence of labels, black-box outputs often are representation vectors whose components do not correspond to any meaningful quantity. Hence, choosing which component(s) to interpret in a label-free unsupervised/self-supervised setting is an important, yet unsolved problem. To bridge this gap in the literature, we introduce two crucial extensions of post-hoc explanation techniques: (1) label-free featur…
Barcelona School of Informatics Universitat Politecnica de Catalunya 08034 Barcelona, Spain Email
Implementing systems based on Machine Learning to detect fraud and other Non-Technical Losses (NTL) is challenging: the data available is biased, and the algorithms currently used are black-boxes that cannot be either easily trusted or understood by stakeholders. This work explains our human-in-the-loop approach to mitigate these problems in a real system that uses a supervised model to detect Non-Technical Losses (NTL) for an international utility company from Spain. This approach exploits human knowledge (e.g. from the data scientists or the company's stakeholders) and the information provid…
The joint optimization of the reconstruction and classification error is a hard non convex problem, especially when a non linear mapping is utilized. In order to overcome this obstacle, a novel optimization strategy is proposed, in which a Convolutional Autoencoder for dimensionality reduction and a classifier composed by a Fully Connected Network, are combined to simultaneously produce supervised dimensionality reduction and predictions. It turned out that this methodology can also be greatly beneficial in enforcing explainability of deep learning architectures. Additionally, the resulting La…
University of Hartford（哈特福德大学）；Tennessee Tech University（田纳西理工大学）；Edith Cowan University（伊迪丝·考恩大学）
The lack of explainability of a decision from an Artificial Intelligence (AI) based "black box" system/model, despite its superiority in many real-world applications, is a key stumbling block for adopting AI in many high stakes applications of different domain or industry. While many popular Explainable Artificial Intelligence (XAI) methods or approaches are available to facilitate a human-friendly explanation of the decision, each has its own merits and demerits, with a plethora of open challenges. We demonstrate popular XAI methods with a mutual case study/task (i.e., credit default predicti…
University of Vienna（维也纳大学）；Volkswagen AG（大众汽车集团）；CAPE Analytics（CAPE分析公司）
Weak supervision is leveraged in a wide range of domains and tasks due to its ability to create massive amounts of labeled data, requiring only little manual effort. Standard approaches use labeling functions to specify signals that are relevant for the labeling. It has been conjectured that weakly supervised models over-rely on those signals and as a result suffer from overfitting. To verify this assumption, we introduce a novel method, XPASC (eXPlainability-Association SCore), for measuring the generalization of a model trained with a weakly supervised dataset. Considering the occurrences of…
In this review, we examine the problem of designing interpretable and explainable machine learning models. Interpretability and explainability lie at the core of many machine learning and statistical applications in medicine, economics, law, and natural sciences. Although interpretability and explainability have escaped a clear universal definition, many techniques motivated by these properties have been developed over the recent 30 years with the focus currently shifting towards deep learning methods. In this review, we emphasise the divide between interpretability and explainability and illu…
University of Toronto（多伦多大学）；Vector Institute for Artificial Intelligence（向量人工智能研究所）；The Hospital for Sick Children（病童医院）
Translating machine learning (ML) models effectively to clinical practice requires establishing clinicians' trust. Explainability, or the ability of an ML model to justify its outcomes and assist clinicians in rationalizing the model prediction, has been generally understood to be critical to establishing trust. However, the field suffers from the lack of concrete definitions for usable explanations in different settings. To identify specific aspects of explainability that may catalyze building trust in ML models, we surveyed clinicians from two distinct acute care specialties (Intenstive Care…
Deep neural networks are typically trained under a supervised learning framework where a model learns a single task using labeled data. Instead of relying solely on labeled data, practitioners can harness unlabeled or related data to improve model performance, which is often more accessible and ubiquitous. Self-supervised pre-training for transfer learning is becoming an increasingly popular technique to improve state-of-the-art results using unlabeled data. It involves first pre-training a model on a large amount of unlabeled data, then adapting the model to target tasks of interest. In this …
Delft University of Technology（代尔夫特理工大学）；University of Copenhagen（哥本哈根大学）
Semi-supervised learning is a setting in which one has labeled and unlabeled data available. In this survey we explore different types of theoretical results when one uses unlabeled data in classification and regression tasks. Most methods that use unlabeled data rely on certain assumptions about the data distribution. When those assumptions are not met in reality, including unlabeled data may actually decrease performance. Studying such methods, it therefore is particularly important to have an understanding of the underlying theory. In this review we gather results about the possible gains o…
Recently self supervised learning has seen explosive growth and use in variety of machine learning tasks because of its ability to avoid the cost of annotating large-scale datasets. This paper gives an overview for best self supervised learning approaches for multimodal learning. The presented approaches have been aggregated by extensive study of the literature and tackle the application of self supervised learning in different ways. The approaches discussed are cross modal generation, cross modal pretraining, cyclic translation, and generating unimodal labels in self supervised fashion.
The successful application of machine learning (ML) methods becomes increasingly dependent on their interpretability or explainability. Designing explainable ML systems is instrumental to ensuring transparency of automated decision-making that targets humans. The explainability of ML methods is also an essential ingredient for trustworthy artificial intelligence. A key challenge in ensuring explainability is its dependence on the specific human user ("explainee"). The users of machine learning methods might have vastly different background knowledge about machine learning principles. One user …
A Survey on Self-Supervised Representation Learning
Technical University of Dortmund（多特蒙德工业大学）；Heinrich Heine University Düsseldorf（杜塞尔多夫海因里希·海涅大学）；Research Center Jülich（于利希研究中心）；Helmholtz AI（亥姆霍兹人工智能（Helmholtz AI））
University of Oxford（牛津大学）；University of Nottingham（诺丁汉大学）
The automotive industry has witnessed an increasing level of development in the past decades; from manufacturing manually operated vehicles to manufacturing vehicles with a high level of automation. With the recent developments in Artificial Intelligence (AI), automotive companies now employ blackbox AI models to enable vehicles to perceive their environments and make driving decisions with little or no input from a human. With the hope to deploy autonomous vehicles (AV) on a commercial scale, the acceptance of AV by society becomes paramount and may largely depend on their degree of transpare…
Fraunhofer IAIS（弗劳恩霍夫智能分析与信息系统研究所）；University of Bonn（波恩大学）；TU Dortmund University（多特蒙德工业大学）
This survey presents an overview of integrating prior knowledge into machine learning systems in order to improve explainability. The complexity of machine learning models has elicited research to make them more explainable. However, most explainability methods cannot provide insight beyond the given data, requiring additional information about the context. We propose to harness prior knowledge to improve upon the explanation capabilities of machine learning models. In this paper, we present a categorization of current research into three main categories which either integrate knowledge into t…
MPI-SWS（马克斯·普朗克软件系统研究所）；University of Maryland（马里兰大学）；Bosch Center for Artificial Intelligence（博世人工智能中心）
As deep neural networks (DNNs) get adopted in an ever-increasing number of applications, explainability has emerged as a crucial desideratum for these models. In many real-world tasks, one of the principal reasons for requiring explainability is to in turn assess prediction robustness, where predictions (i.e., class labels) that do not conform to their respective explanations (e.g., presence or absence of a concept in the input) are deemed to be unreliable. However, most, if not all, prior methods for checking explanation-conformity (e.g., LIME, TCAV, saliency maps) require significant manual …
Indian Institute of Technology, Hyderabad（印度理工学院海得拉巴分校）
Explainability has been widely stated as a cornerstone of the responsible and trustworthy use of machine learning models. With the ubiquitous use of Deep Neural Network (DNN) models expanding to risk-sensitive and safety-critical domains, many methods have been proposed to explain the decisions of these models. Recent years have also seen concerted efforts that have shown how such explanations can be distorted (attacked) by minor input perturbations. While there have been many surveys that review explainability methods themselves, there has been no effort hitherto to assimilate the different m…
Mila（米拉人工智能研究所）；DIRO, Université de Montréal（蒙特利尔大学计算机科学与运筹学系）；ServiceNow（ServiceNow公司）
Labeling data is often expensive and time-consuming, especially for tasks such as object detection and instance segmentation, which require dense labeling of the image. While few-shot object detection is about training a model on novel (unseen) object classes with little data, it still requires prior training on many labeled examples of base (seen) classes. On the other hand, self-supervised methods aim at learning representations from unlabeled data which transfer well to downstream tasks such as object detection. Combining few-shot and self-supervised object detection is a promising research…
Univ Lyon（里昂大学）；ENSL（里昂高等师范学院）；CNRS（法国国家科学研究中心）；EPFL（洛桑联邦理工学院）；ENS de Lyon（里昂高等师范学院）
Understanding the molecular processes that drive cellular life is a fundamental question in biological research. Ambitious programs have gathered a number of molecular datasets on large populations. To decipher the complex cellular interactions, recent work has turned to supervised machine learning methods. The scientific questions are formulated as classical learning problems on tabular data or on graphs, e.g. phenotype prediction from gene expression data. In these works, the input features on which the individual predictions are predominantly based are often interpreted as indicative of the…
Shanghai University of Finance and Economics（上海财经大学）；University of Science and Technology of China（中国科学技术大学）；University of Illinois Chicago（伊利诺伊大学芝加哥分校）；Carnegie Mellon University（卡内基梅隆大学）
Anomaly detection (AD) is a crucial task in machine learning with various applications, such as detecting emerging diseases, identifying financial frauds, and detecting fake news. However, obtaining complete, accurate, and precise labels for AD tasks can be expensive and challenging due to the cost and difficulties in data annotation. To address this issue, researchers have developed AD methods that can work with incomplete, inexact, and inaccurate supervision, collectively summarized as weakly supervised anomaly detection (WSAD) methods. In this study, we present the first comprehensive surve…
Central Washington University（中央华盛顿大学）；University of Washington Tacoma（华盛顿大学塔科马分校）；Kensci Inc.（Kensci公司）
This paper surveys visual methods of explainability of Machine Learning (ML) with focus on moving from quasi-explanations that dominate in ML to domain-specific explanation supported by granular visuals. ML interpretation is fundamentally a human activity and visual methods are more readily interpretable. While efficient visual representations of high-dimensional data exist, the loss of interpretable information, occlusion, and clutter continue to be a challenge, which lead to quasi-explanations. We start with the motivation and the different definitions of explainability. The paper focuses on…
The past century was era of linear systems. Either systems (especially industrial ones) were simple (quasi)linear or linear approximations were accurate enough. In addition, just at the ending decades of the century profusion of computing devices were available, before then due to lack of computational resources it was not easy to evaluate available nonlinear system studies. At the moment both these two conditions changed, systems are highly complex and also pervasive amount of computation strength is cheap and easy to achieve. For recent era, a new branch of supervised learning well known as …
University of Toronto（多伦多大学）；Electrical and Computer Engineering（电子与计算机工程（此处为院系，按要求不提取，但原文中该部分是否为机构？根据规则，机构粒度提取到大学/学院/公司/研究院级别即可，不要细拆到系等，因此仅保留“University of Toronto”））
With the rise of artificial intelligence and machine learning in modern computing, one of the major concerns regarding such techniques is to provide privacy and security against adversaries. We present this survey paper to cover the most representative papers in poisoning attacks against supervised machine learning models. We first provide a taxonomy to categorize existing studies and then present detailed summaries for selected papers. We summarize and compare the methodology and limitations of existing literature. We conclude this paper with potential improvements and future directions to fu…
University of Tübingen（图宾根大学）；University of Surrey（萨里大学）；MPI for Informatics（马克斯·普朗克信息学研究所）；MPI for Intelligent Systems（马克斯·普朗克智能系统研究所）
State-of-the-art deep learning models are often trained with a large amount of costly labeled training data. However, requiring exhaustive manual annotations may degrade the model's generalizability in the limited-label regime. Semi-supervised learning and unsupervised learning offer promising paradigms to learn from an abundance of unlabeled visual data. Recent progress in these paradigms has indicated the strong benefits of leveraging unlabeled data to improve model generalization and provide better model initialization. In this survey, we review the recent advanced deep learning algorithms …
Lesion segmentation is a core task for quantitative analysis of MRI scans of Multiple Sclerosis patients. The recent success of deep learning techniques in a variety of medical image analysis applications has renewed community interest in this challenging problem and led to a burst of activity for new algorithm development. In this survey, we investigate the supervised CNN-based methods for MS lesion segmentation. We decouple these reviewed works into their algorithmic components and discuss each separately. For methods that provide evaluations on public benchmark datasets, we report compariso…
Masked autoencoders are scalable vision learners, as the title of MAE \cite{he2022masked}, which suggests that self-supervised learning (SSL) in vision might undertake a similar trajectory as in NLP. Specifically, generative pretext tasks with the masked prediction (e.g., BERT) have become a de facto standard SSL practice in NLP. By contrast, early attempts at generative methods in vision have been buried by their discriminative counterparts (like contrastive learning); however, the success of mask image modeling has revived the masking autoencoder (often termed denoising autoencoder in the pa…
Deep learning has been the subject of growing interest in recent years. Specifically, a specific type called Multimodal learning has shown great promise for solving a wide range of problems in domains such as language, vision, audio, etc. One promising research direction to improve this further has been learning rich and robust low-dimensional data representation of the high-dimensional world with the help of large-scale datasets present on the internet. Because of its potential to avoid the cost of annotating large-scale datasets, self-supervised learning has been the de facto standard for th…
Supervised Algorithmic Fairness in Distribution Shifts: A Survey
School of New Media and Communication, Tianjin University（天津大学新媒体与传播学院）；College of Intelligence and Computing, Tianjin University（天津大学智能与计算学部）；Department of Computer Science, Baylor University（贝勒大学计算机系）；Electrical Engineering and Computer Science Department, University of Arkansas（阿肯色大学电气与计算机科学系）
University of Waikato（怀卡托大学）；Warsaw University of Technology（华沙工业大学）；University of São Paulo（圣保罗大学）；École Polytechnique（巴黎综合理工学院）；Institut Polytechnique de Paris（巴黎理工学院）；Télécom Paris（巴黎电信学院）
Unlabelled data appear in many domains and are particularly relevant to streaming applications, where even though data is abundant, labelled data is rare. To address the learning problems associated with such data, one can ignore the unlabelled data and focus only on the labelled data (supervised learning); use the labelled data and attempt to leverage the unlabelled data (semi-supervised learning); or assume some labels will be available on request (active learning). The first approach is the simplest, yet the amount of labelled data available will limit the predictive performance. The second…
University of Electronic Science and Technology of China（电子科技大学）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；Peng Cheng Lab（鹏城实验室）；The Chinese University of Hong Kong（香港中文大学）
Classifier-Free Diffusion-Based Weakly-Supervised Approach for Health Indicator Derivation in Rotating Machines: Advancing Early Fault Detection and Condition Monitoring
