Deep learning as represented by the artificial deep neural networks (DNNs) has achieved great success in many important areas that deal with text, images, videos, graphs, and so on. However, the black-box nature of DNNs has become one of the primary obstacles for their wide acceptance in mission-critical applications such as medical diagnosis and therapy. Due to the huge potential of deep learning, interpreting neural networks has recently attracted much research attention. In this paper, based on our comprehensive taxonomy, we systematically review recent studies in understanding the mechanism of neural networks, describe applications of interpretability especially in medicine, and discuss future directions of interpretability research, such as in relation to fuzzy logic and brain science.
In this work, we formulate NEWRON: a generalization of the McCulloch-Pitts neuron structure. This new framework aims to explore additional desirable properties of artificial neurons. We show that some specializations of NEWRON allow the network to be interpretable with no change in their expressiveness. By just inspecting the models produced by our NEWRON-based networks, we can understand the rules governing the task. Extensive experiments show that the quality of the generated models is better than traditional interpretable models and in line or better than standard neural networks.
Guangdong Key Laboratory of Brain-Inspired Intelligent Computation（广东省脑启发智能计算重点实验室）；Southern University of Science and Technology（南方科技大学）；Research Institute of Trust-worthy Autonomous Systems（可信自主系统研究所）；School of Computer Science, University of Birmingham（伯明翰大学计算机科学学院）
Along with the great success of deep neural networks, there is also growing concern about their black-box nature. The interpretability issue affects people's trust on deep learning systems. It is also related to many ethical problems, e.g., algorithmic discrimination. Moreover, interpretability is a desired property for deep networks to become powerful tools in other research fields, e.g., drug discovery and genomics. In this survey, we conduct a comprehensive review of the neural network interpretability research. We first clarify the definition of interpretability as it has been used in many…
Multilevel Interpretability Of Artificial Neural Networks: Leveraging Framework And Methods From Neuroscience
University of Cambridge（剑桥大学）；University of Oxford（牛津大学）；Imperial College London（帝国理工学院）；Massachusetts Institute of Technology（麻省理工学院）；Georgia Institute of Technology（佐治亚理工学院）；New York University（纽约大学）；Princeton University（普林斯顿大学）
In recent years, with the advent of massive computational power and the availability of huge amounts of data, Deep neural networks have enabled the exploration of uncharted areas in several domains. But at times, they under-perform due to insufficient data, poor data quality, data that might not be covering the domain broadly, etc. Knowledge-based systems leverage expert knowledge for making decisions and suitably take actions. Such systems retain interpretability in the decision-making process. This paper focuses on exploring techniques to integrate expert knowledge to the Deep Neural Network…
University of North Carolina at Charlotte（北卡罗来纳大学夏洛特分校）
Modern deep learning algorithms tend to optimize an objective metric, such as minimize a cross entropy loss on a training dataset, to be able to learn. The problem is that the single metric is an incomplete description of the real world tasks. The single metric cannot explain why the algorithm learn. When an erroneous happens, the lack of interpretability causes a hardness of understanding and fixing the error. Recently, there are works done to tackle the problem of interpretability to provide insights into neural networks behavior and thought process. The works are important to identify poten…
Ongoing efforts to understand deep neural networks (DNN) have provided many insights, but DNNs remain incompletely understood. Improving DNN's interpretability has practical benefits, such as more accountable usage, better algorithm maintenance and improvement. The complexity of dataset structure may contribute to the difficulty in solving interpretability problem arising from DNN's black-box mechanism. Thus, we propose to use pattern theory formulated by Ulf Grenander, in which data can be described as configurations of fundamental objects that allow us to investigate convolutional neural net…
Maastricht University（马斯特里赫特大学）；Maastricht University Medical Centre+（马斯特里赫特大学医学中心+）
Artificial Intelligence has emerged as a useful aid in numerous clinical applications for diagnosis and treatment decisions. Deep neural networks have shown same or better performance than clinicians in many tasks owing to the rapid increase in the available data and computational power. In order to conform to the principles of trustworthy AI, it is essential that the AI system be transparent, robust, fair and ensure accountability. Current deep neural solutions are referred to as black-boxes due to a lack of understanding of the specifics concerning the decision making process. Therefore, the…
Institute for Information Systems, FHNW University of Applied Sciences and Arts Northwestern Switzerland（瑞士西北应用科学与艺术大学信息系统研究所）；Chair for Philosophy, ETH Zurich（苏黎世联邦理工学院哲学教席）
Many computer models such as cellular automata and artificial neural networks have been developed and successfully applied. However, in some cases, these models might be restrictive on the possible solutions or their solutions might be difficult to interpret. To overcome this problem, we outline a new approach, the so-called allagmatic method, that automatically programs and executes models with as little limitations as possible while maintaining human interpretability. Earlier we described a metamodel and its building blocks according to the philosophical concepts of structure (spatial dimens…
The practical application of deep neural networks are still limited by their lack of transparency. One of the efforts to provide explanation for decisions made by artificial intelligence (AI) is the use of saliency or heat maps highlighting relevant regions that contribute significantly to its prediction. A layer-wise amplitude filtering method was previously introduced to improve the quality of heatmaps, performing error corrections by noise-spike suppression. In this study, we generalize the layerwise error correction by considering any identifiable error and assuming there exists a groundtr…
University of Texas at Austin（德克萨斯大学奥斯汀分校）；CognitiveScale
As artificial intelligence plays an increasingly important role in our society, there are ethical and moral obligations for both businesses and researchers to ensure that their machine learning models are designed, deployed, and maintained responsibly. These models need to be rigorously audited for fairness, robustness, transparency, and interpretability. A variety of methods have been developed that focus on these issues in isolation, however, managing these methods in conjunction with model development can be cumbersome and timeconsuming. In this paper, we introduce a unified and model-agnos…
Nanyang Technological University（南洋理工大学）；Alibaba Group Holding Limited（阿里巴巴集团控股有限公司）
Recently, artificial intelligence and machine learning in general have demonstrated remarkable performances in many tasks, from image processing to natural language processing, especially with the advent of deep learning. Along with research progress, they have encroached upon many different fields and disciplines. Some of them require high level of accountability and thus transparency, for example the medical sector. Explanations for machine decisions and predictions are thus needed to justify their reliability. This requires greater interpretability, which often means we need to understand t…
The increasing capabilities of artificial intelligence (AI) systems make it ever more important that we interpret their internals to ensure that their intentions are aligned with human values. Yet there is reason to believe that misaligned artificial intelligence will have a convergent instrumental incentive to make its thoughts difficult for us to interpret. In this article, I discuss many ways that a capable AI might circumvent scalable interpretability methods and suggest a framework for thinking about these potential future risks.
University of Liverpool（利物浦大学）；University of Oxford（牛津大学）；Lancaster University（兰卡斯特大学）；Defence Science and Technology Laboratory (Dstl)（国防科学技术实验室）；Queen’s University Belfast（贝尔法斯特女王大学）
In the past few years, significant progress has been made on deep neural networks (DNNs) in achieving human-level performance on several long-standing tasks. With the broader deployment of DNNs on various applications, the concerns over their safety and trustworthiness have been raised in public, especially after the widely reported fatal incidents involving self-driving cars. Research to address these concerns is particularly active, with a significant number of papers released in the past few years. This survey paper conducts a review of the current research effort into making DNNs safe and …
Machine learning models have become more and more complex in order to better approximate complex functions. Although fruitful in many domains, the added complexity has come at the cost of model interpretability. The once popular k-nearest neighbors (kNN) approach, which finds and uses the most similar data for reasoning, has received much less attention in recent decades due to numerous problems when compared to other techniques. We show that many of these historical problems with kNN can be overcome, and our contribution has applications not only in machine learning but also in online learnin…
Interpretation of deep learning models is a very challenging problem because of their large number of parameters, complex connections between nodes, and unintelligible feature representations. Despite this, many view interpretability as a key solution to trustworthiness, fairness, and safety, especially as deep learning is applied to more critical decision tasks like credit approval, job screening, and recidivism prediction. There is an abundance of good research providing interpretability to deep learning models; however, many of the commonly used methods do not consider a phenomenon called "…
Towards Intrinsic Interpretability of Large Language Models:A Survey of Design Principles and Architectures
MOE Key Lab of Computational Linguistics, Peking University（计算语言学MOE实验室，北京大学）；Beijing Academy of Artificial Intelligence, Beijing, China（北京人工智能研究院，北京，中国）；Nanjing University of Science and Technology（南京理工大学）；Purdue University（普渡大学）
EXplainable AI (XAI) methods have been proposed to interpret how a deep neural network predicts inputs through model saliency explanations that highlight the parts of the inputs deemed important to arrive a decision at a specific target. However, it remains challenging to quantify correctness of their interpretability as current evaluation approaches either require subjective input from humans or incur high computation cost with automated evaluation. In this paper, we propose backdoor trigger patterns--hidden malicious functionalities that cause misclassification--to automate the evaluation of…
There has recently been a surge of work in explanatory artificial intelligence (XAI). This research area tackles the important problem that complex machines and algorithms often cannot provide insights into their behavior and thought processes. XAI allows users and parts of the internal system to be more transparent, providing explanations of their decisions in some level of detail. These explanations are important to ensure algorithmic fairness, identify potential bias/problems in the training data, and to ensure that the algorithms perform as expected. However, explanations produced by these…
Discovering Chunks in Neural Embeddings for Interpretability
Explainable Machine Learning Lab, Helmholtz Munich（慕尼黑亥姆霍兹大学可解释机器学习实验室）；Technical University of Munich（慕尼黑工业大学）；Institute for Human-Centered AI, Helmholtz Munich（慕尼黑亥姆霍兹以人为本人工智能研究所）；Max Planck Institute for Biological Cybernetics（马克斯·普朗克生物控制论研究所）；Munich Center for Machine Learning（慕尼黑机器学习中心）
Arizona State University（亚利桑那州立大学）；Army Research Lab（陆军研究实验室）
Machine learning models have had discernible achievements in a myriad of applications. However, most of these models are black-boxes, and it is obscure how the decisions are made by them. This makes the models unreliable and untrustworthy. To provide insights into the decision making processes of these models, a variety of traditional interpretable models have been proposed. Moreover, to generate more human-friendly explanations, recent work on interpretability tries to answer questions related to causality such as "Why does this model makes such decisions?" or "Was it a specific feature that …
Machine learning applied to generate data-driven models are lacking of transparency leading the process engineer to lose confidence in relying on the model predictions to optimize his industrial process. Bringing processes in the industry to a certain level of autonomy using data-driven models is particularly challenging as the first user of those models, is the expert in the process with often decades of experience. It is necessary to expose to the process engineer, not solely the model predictions, but also their interpretability. To that end, several approaches have been proposed in the lit…
University of Coimbra（科英布拉大学）；Institute of Systems and Robotics（系统与机器人研究所）；Radboud University（拉德堡德大学）
Regression problems have been more and more embraced by deep learning (DL) techniques. The increasing number of papers recently published in this domain, including surveys and reviews, shows that deep regression has captured the attention of the community due to efficiency and good accuracy in systems with high-dimensional data. However, many DL methodologies have complex structures that are not readily transparent to human users. Accessing the interpretability of these models is an essential factor for addressing problems in sensitive areas such as cyber-security systems, medical, financial s…
Milliman（Milliman公司）；SCOR（SCOR公司）；Laboratoire de Mathématiques de Bretagne Atlantique（布列塔尼大西洋数学实验室）；Univ Brest（布雷斯特大学）
The use of models, even if efficient, must be accompanied by an understanding at all levels of the process that transforms data (upstream and downstream). Thus, needs increase to define the relationships between individual data and the choice that an algorithm could make based on its analysis (e.g. the recommendation of one product or one promotional offer, or an insurance rate representative of the risk). Model users must ensure that models do not discriminate and that it is also possible to explain their results. This paper introduces the importance of model interpretation and tackles the no…
A Comprehensive Survey on Self-Interpretable Neural Networks
Artificial Intelligence Thrust, The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）人工智能方向）；Computer Network Information Center, Chinese Academy of Sciences（中国科学院计算机网络信息中心）
Karlsruhe Institute of Technology (KIT)（卡尔斯鲁厄理工学院）
By definition, outliers are rarely observed in reality, making them difficult to detect or analyse. Artificial outliers approximate such genuine outliers and can, for instance, help with the detection of genuine outliers or with benchmarking outlier-detection algorithms. The literature features different approaches to generate artificial outliers. However, systematic comparison of these approaches remains absent. This surveys and compares these approaches. We start by clarifying the terminology in the field, which varies from publication to publication, and we propose a general problem formula…
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…
Zhejiang University（浙江大学）；National University of Singapore（新加坡国立大学）；Zhejiang Lab（之江实验室）
Neural networks (NNs) and decision trees (DTs) are both popular models of machine learning, yet coming with mutually exclusive advantages and limitations. To bring the best of the two worlds, a variety of approaches are proposed to integrate NNs and DTs explicitly or implicitly. In this survey, these approaches are organized in a school which we term as neural trees (NTs). This survey aims to present a comprehensive review of NTs and attempts to identify how they enhance the model interpretability. We first propose a thorough taxonomy of NTs that expresses the gradual integration and co-evolut…
Artificial intelligence (AI) has been transforming the practice of drug discovery in the past decade. Various AI techniques have been used in a wide range of applications, such as virtual screening and drug design. In this survey, we first give an overview on drug discovery and discuss related applications, which can be reduced to two major tasks, i.e., molecular property prediction and molecule generation. We then discuss common data resources, molecule representations and benchmark platforms. Furthermore, to summarize the progress of AI in drug discovery, we present the relevant AI technique…
In the meantime, a wide variety of terminologies, motivations, approaches, and evaluation criteria have been developed within the research field of explainable artificial intelligence (XAI). With the amount of XAI methods vastly growing, a taxonomy of methods is needed by researchers as well as practitioners: To grasp the breadth of the topic, compare methods, and to select the right XAI method based on traits required by a specific use-case context. Many taxonomies for XAI methods of varying level of detail and depth can be found in the literature. While they often have a different focus, the…
School of Computer Science, College of Science and Health, Technological University Dublin（都柏林理工大学科学与健康学院计算机科学学院）；Technological University Dublin（都柏林理工大学）
Explainable Artificial Intelligence (XAI) has experienced a significant growth over the last few years. This is due to the widespread application of machine learning, particularly deep learning, that has led to the development of highly accurate models but lack explainability and interpretability. A plethora of methods to tackle this problem have been proposed, developed and tested. This systematic review contributes to the body of knowledge by clustering these methods with a hierarchical classification system with four main clusters: review articles, theories and notions, methods and their ev…
Interplay between Federated Learning and Explainable Artificial Intelligence: a Scoping Review
Simula Metropolitan Center for Digital Engineering（西米拉数字工程中心）；Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；University Hospital Bonn（波恩大学医院）；Norwegian University of Science and Technology（挪威科技大学）；Charité - Universitätsmedizin Berlin（柏林夏里特医学院）；Birmingham City University（伯明翰城市大学）；ETH Zurich（苏黎世联邦理工学院）；Technical University of Munich（慕尼黑工业大学）
When will the mist clear? On the Interpretability of Machine Learning for Medical Applications: a survey
Universidad Católica de Murcia (UCAM)（穆尔西亚天主教大学）；Universitatea Alexandru Ioan Cuza (UAIC)（亚历山德鲁·伊万·库扎大学）；IRCCS San Raffaele Pisana（圣拉斐尔皮萨纳科学住院与治疗研究所）；San Raffaele Roma Open University（罗马圣拉斐尔开放大学）
Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University（北京交通大学智能交通信息安全与隐私保护北京市重点实验室）
Malware is being increasingly threatening and malware detectors based on traditional signature-based analysis are no longer suitable for current malware detection. Recently, the models based on machine learning (ML) are developed for predicting unknown malware variants and saving human strength. However, most of the existing ML models are black-box, which made their pre-diction results undependable, and therefore need further interpretation in order to be effectively deployed in the wild. This paper aims to examine and categorize the existing researches on ML-based malware detector interpretab…
St. Pölten University of Applied Sciences（圣帕尔滕应用科学大学）；University of Campania “Luigi Vanvitelli”（坎帕尼亚大学“路易吉·万维泰利”）；University of Molise（莫利塞大学）
Artificial intelligence (AI) systems are becoming critical components of today's IT landscapes. Their resilience against attacks and other environmental influences needs to be ensured just like for other IT assets. Considering the particular nature of AI, and machine learning (ML) in particular, this paper provides an overview of the emerging field of resilient AI and presents research issues the authors identify as potential future work.
Most complex machine learning and modelling techniques are prone to over-fitting and may subsequently generalise poorly to future data. Artificial neural networks are no different in this regard and, despite having a level of implicit regularisation when trained with gradient descent, often require the aid of explicit regularisers. We introduce a new framework, Model Gradient Similarity (MGS), that (1) serves as a metric of regularisation, which can be used to monitor neural network training, (2) adds insight into how explicit regularisers, while derived from widely different principles, opera…
ENSTA Paris, Institut Polytechnique Paris（巴黎高等先进技术学院，巴黎综合理工学院）；Inria Flowers（法国国家信息与自动化研究所Flowers团队）；Renault（雷诺公司）；TECNALIA（TECNALIA研究中心）；Basque Research and Technology Alliance (BRTA)（巴斯克研究与技术联盟）；University of the Basque Country (UPV/EHU)（巴斯克大学）
Most of state of the art methods applied on time series consist of deep learning methods that are too complex to be interpreted. This lack of interpretability is a major drawback, as several applications in the real world are critical tasks, such as the medical field or the autonomous driving field. The explainability of models applied on time series has not gather much attention compared to the computer vision or the natural language processing fields. In this paper, we present an overview of existing explainable AI (XAI) methods applied on time series and illustrate the type of explanations …
The rise of social media platforms provides an unbounded, infinitely rich source of aggregate knowledge of the world around us, both historic and real-time, from a human perspective. The greatest challenge we face is how to process and understand this raw and unstructured data, go beyond individual observations and see the "big picture"--the domain of Situation Awareness. We provide an extensive survey of Artificial Intelligence research, focusing on microblog social media data with applications to Situation Awareness, that gives the seminal work and state-of-the-art approaches across six them…
Baidu Research, Baidu Inc.（百度公司百度研究院）；University of Pennsylvania（宾夕法尼亚大学）；Tsinghua University（清华大学）；University of Oregon（俄勒冈大学）
Deep neural networks have been well-known for their superb handling of various machine learning and artificial intelligence tasks. However, due to their over-parameterized black-box nature, it is often difficult to understand the prediction results of deep models. In recent years, many interpretation tools have been proposed to explain or reveal how deep models make decisions. In this paper, we review this line of research and try to make a comprehensive survey. Specifically, we first introduce and clarify two basic concepts -- interpretations and interpretability -- that people usually get co…
University of North Carolina at Charlotte（北卡罗来纳大学夏洛特分校）
In this survey paper, we overview major deep learning methods used in Natural Language Processing (NLP) and source code over the last 35 years. Next, we present a survey of the applications of Artificial Intelligence (AI) for source code, also known as Code Intelligence (CI) and Programming Language Processing (PLP). We survey over 287 publications and present a software-engineering centered taxonomy for CI placing each of the works into one category describing how it best assists the software development cycle. Then, we overview the field of conversational assistants and their applications in…
