Today, machine learning (ML) models are increasingly applied in decision making. This induces an urgent need for quality assurance of ML models with respect to (often domain-dependent) requirements. Monotonicity is one such requirement. It specifies a software as 'learned' by an ML algorithm to give an increasing prediction with the increase of some attribute values. While there exist multiple ML algorithms for ensuring monotonicity of the generated model, approaches for checking monotonicity, in particular of black-box models, are largely lacking. In this work, we propose verification-based testing of monotonicity, i.e., the formal computation of test inputs on a white-box model via verification technology, and the automatic inference of this approximating white-box model from the black-box model under test. On the white-box model, the space of test inputs can be systematically explored by a directed computation of test cases. The empirical evaluation on 90 black-box models shows verification-based testing can outperform adaptive random testing as well as property-based techniques with respect to effectiveness and efficiency.
Columbia University（哥伦比亚大学）；Purdue University（普渡大学）；Courant Institute of Mathematical Sciences, New York University（纽约大学库朗数学科学研究所）；Duquesne University（杜肯大学）
A Boolean $k$-monotone function defined over a finite poset domain ${\cal D}$ alternates between the values $0$ and $1$ at most $k$ times on any ascending chain in ${\cal D}$. Therefore, $k$-monotone functions are natural generalizations of the classical monotone functions, which are the $1$-monotone functions. Motivated by the recent interest in $k$-monotone functions in the context of circuit complexity and learning theory, and by the central role that monotonicity testing plays in the context of property testing, we initiate a systematic study of $k$-monotone functions, in the property test…
We propose an algorithm for a family of optimization problems where the objective can be decomposed as a sum of functions with monotonicity properties. The motivating problem is optimization of hyperparameters of machine learning algorithms, where we argue that the objective, validation error, can be decomposed as monotonic functions of the hyperparameters. Our proposed algorithm adapts Bayesian optimization methods to incorporate the monotonicity constraints. We illustrate the advantages of exploiting monotonicity using illustrative examples and demonstrate the improvements in optimization ef…
We demonstrate how easy it is for modern machine-learned systems to violate common deontological ethical principles and social norms such as "favor the less fortunate," and "do not penalize good attributes." We propose that in some cases such ethical principles can be incorporated into a machine-learned model by adding shape constraints that constrain the model to respond only positively to relevant inputs. We analyze the relationship between these deontological constraints that act on individuals and the consequentialist group-based fairness goals of one-sided statistical parity and equal opp…
Over the last two decades, submodular function maximization has been the workhorse of many discrete optimization problems in machine learning applications. Traditionally, the study of submodular functions was based on binary function properties. However, such properties have an inherit weakness, namely, if an algorithm assumes functions that have a particular property, then it provides no guarantee for functions that violate this property, even when the violation is very slight. Therefore, recent works began to consider continuous versions of function properties. Probably the most significant …
The increasing usage of machine learning models raises the question of the reliability of these models. The current practice of testing with limited data is often insufficient. In this paper, we provide a framework for automated test data synthesis to test black-box ML/DL models. We address an important challenge of generating realistic user-controllable data with model agnostic coverage criteria to test a varied set of properties, essentially to increase trust in machine learning models. We experimentally demonstrate the effectiveness of our technique.
Machine learning has become prevalent across a wide variety of applications. Unfortunately, machine learning has also shown to be susceptible to deception, leading to errors, and even fatal failures. This circumstance calls into question the widespread use of machine learning, especially in safety-critical applications, unless we are able to assure its correctness and trustworthiness properties. Software verification and testing are established technique for assuring such properties, for example by detecting errors. However, software testing challenges for machine learning are vast and profuse…
Physics-constrained machine learning is emerging as an important topic in the field of machine learning for physics. One of the most significant advantages of incorporating physics constraints into machine learning methods is that the resulting model requires significantly less data to train. By incorporating physical rules into the machine learning formulation itself, the predictions are expected to be physically plausible. Gaussian process (GP) is perhaps one of the most common methods in machine learning for small datasets. In this paper, we investigate the possibility of constraining a GP …
University College London（伦敦大学学院）；Facebook London（Facebook伦敦）；Kyushu University（九州大学）；Nanyang Technological University（南洋理工大学）
This paper provides a comprehensive survey of Machine Learning Testing (ML testing) research. It covers 144 papers on testing properties (e.g., correctness, robustness, and fairness), testing components (e.g., the data, learning program, and framework), testing workflow (e.g., test generation and test evaluation), and application scenarios (e.g., autonomous driving, machine translation). The paper also analyses trends concerning datasets, research trends, and research focus, concluding with research challenges and promising research directions in ML testing.
Singapore University of Technology and Design（新加坡科技设计大学）
The massive progress of machine learning has seen its application over a variety of domains in the past decade. But how do we develop a systematic, scalable and modular strategy to validate machine-learning systems? We present, to the best of our knowledge, the first approach, which provides a systematic test framework for machine-learning systems that accepts grammar-based inputs. Our OGMA approach automatically discovers erroneous behaviours in classifiers and leverages these erroneous behaviours to improve the respective models. OGMA leverages inherent robustness properties present in any w…
Testing practices within the machine learning (ML) community have centered around assessing a learned model's predictive performance measured against a test dataset, often drawn from the same distribution as the training dataset. While recent work on robustness and fairness testing within the ML community has pointed to the importance of testing against distributional shifts, these efforts also focus on estimating the likelihood of the model making an error against a reference dataset/distribution. We argue that this view of testing actively discourages researchers and developers from looking …
Testing has been widely recognised as difficult for AI applications. This paper proposes a set of testing strategies for testing machine learning applications in the framework of the datamorphism testing methodology. In these strategies, testing aims at exploring the data space of a classification or clustering application to discover the boundaries between classes that the machine learning application defines. This enables the tester to understand precisely the behaviour and function of the software under test. In the paper, three variants of exploratory strategies are presented with the algo…
University of Oxford（牛津大学）；Tencent AI R&D Centre（腾讯人工智能研发中心）
In machine learning (ML) workflows, determining the invariance qualities of an ML model is a common testing procedure. Traditionally, invariance qualities are evaluated using simple formula-based scores, e.g., accuracy. In this paper, we show that testing the invariance qualities of ML models may result in complex visual patterns that cannot be classified using simple formulas. In order to test ML models by analyzing such visual patterns automatically using other ML models, we propose a systematic framework that is applicable to a variety of invariance qualities. We demonstrate the effectivene…
National Security Institute, Virginia Tech（弗吉尼亚理工学院国家安全研究所）；The MITRE Corporation（米特雷公司）
This paper demonstrates the systematic use of combinatorial coverage for selecting and characterizing test and training sets for machine learning models. The presented work adapts combinatorial interaction testing, which has been successfully leveraged in identifying faults in software testing, to characterize data used in machine learning. The MNIST hand-written digits data is used to demonstrate that combinatorial coverage can be used to select test sets that stress machine learning model performance, to select training sets that lead to robust model performance, and to select data for fine-…
MIT Computer Science and Artificial Intelligence Lab（麻省理工学院计算机科学与人工智能实验室）；Harvard Medical School（哈佛医学院）；Massachusetts General Hospital（马萨诸塞总医院）；MGB HealthCare System（MGB医疗系统）；Northwestern University（西北大学）
Objective: Reflex testing protocols allow clinical laboratories to perform second line diagnostic tests on existing specimens based on the results of initially ordered tests. Reflex testing can support optimal clinical laboratory test ordering and diagnosis. In current clinical practice, reflex testing typically relies on simple "if-then" rules; however, this limits their scope since most test ordering decisions involve more complexity than a simple rule will allow. Here, using the analyte ferritin as an example, we propose an alternative machine learning-based approach to "smart" reflex testi…
Machine learning contrasts with traditional software development in that the oracle is the data, and the data is not always a correct representation of the problem that machine learning tries to model. We present a survey of the oracle issues found in machine learning and state-of-the-art solutions for dealing with these issues. These include lines of research for differential testing, metamorphic testing, and test coverage. We also review some recent improvements to robustness during modeling that reduce the impact of oracle issues, as well as tools and frameworks for assisting in testing and…
TU Clausthal（克劳斯塔尔工业大学）；University of Goettingen（哥廷根大学）
Machine learning is nowadays a standard technique for data analysis within software applications. Software engineers need quality assurance techniques that are suitable for these new kinds of systems. Within this article, we discuss the question whether standard software testing techniques that have been part of textbooks since decades are also useful for the testing of machine learning software. Concretely, we try to determine generic and simple smoke tests that can be used to assert that basic functions can be executed without crashing. We found that we can derive such tests using techniques…
We have recently witnessed tremendous success of Machine Learning (ML) in practical applications. Computer vision, speech recognition and language translation have all seen a near human level performance. We expect, in the near future, most business applications will have some form of ML. However, testing such applications is extremely challenging and would be very expensive if we follow today's methodologies. In this work, we present an articulation of the challenges in testing ML based applications. We then present our solution approach, based on the concept of Metamorphic Testing, which aim…
There is a growing body of research indicating the potential of machine learning to tackle complex software testing challenges. One such challenge pertains to continuous integration testing, which is highly time-constrained, and generates a large amount of data coming from iterative code commits and test runs. In such a setting, we can use plentiful test data for training machine learning predictors to identify test cases able to speed up the detection of regression bugs introduced during code integration. However, different machine learning models can have different fault prediction performan…
University of Gothenburg（哥德堡大学）；CNR-IPCF, Istituto per i Processi Chimico-Fisici（意大利国家研究委员会化学物理过程研究所）
Containment of epidemic outbreaks entails great societal and economic costs. Cost-effective containment strategies rely on efficiently identifying infected individuals, making the best possible use of the available testing resources. Therefore, quickly identifying the optimal testing strategy is of critical importance. Here, we demonstrate that machine learning can be used to identify which individuals are most beneficial to test, automatically and dynamically adapting the testing strategy to the characteristics of the disease outbreak. Specifically, we simulate an outbreak using the archetypa…
Cash App, Block（Cash App，Block）；Vector Institute for Artificial Intelligence（向量人工智能研究所）；University of Ottawa（渥太华大学）；University of Victoria（维多利亚大学）
We discuss our simulation tool, fintech-kMC, which is designed to generate synthetic data for machine learning model development and testing. fintech-kMC is an agent-based model driven by a kinetic Monte Carlo (a.k.a. continuous time Monte Carlo) engine which simulates the behaviour of customers using an online digital financial platform. The tool provides an interpretable, reproducible, and realistic way of generating synthetic data which can be used to validate and test AI/ML models and pipelines to be used in real-world customer-facing financial applications.
Deepchecks Ltd.（Deepchecks有限公司）；Ben-Gurion University of the Negev（内盖夫本-古里安大学）
This paper presents Deepchecks, a Python library for comprehensively validating machine learning models and data. Our goal is to provide an easy-to-use library comprising of many checks related to various types of issues, such as model predictive performance, data integrity, data distribution mismatches, and more. The package is distributed under the GNU Affero General Public License (AGPL) and relies on core libraries from the scientific Python ecosystem: scikit-learn, PyTorch, NumPy, pandas, and SciPy. Source code, documentation, examples, and an extensive user guide can be found at \url{htt…
TU Clausthal（克劳斯塔尔工业大学）；University of Goettingen（哥廷根大学）
Context: Differential testing is a useful approach that uses different implementations of the same algorithms and compares the results for software testing. In recent years, this approach was successfully used for test campaigns of deep learning frameworks. Objective: There is little knowledge on the application of differential testing beyond deep learning. Within this article, we want to close this gap for classification algorithms. Method: We conduct a case study using Scikit-learn, Weka, Spark MLlib, and Caret in which we identify the potential of differential testing by considering which a…
Automated machine learning (AutoML) systems aim at finding the best machine learning (ML) pipeline that automatically matches the task and data at hand. We investigate the robustness of machine learning pipelines generated with three AutoML systems, TPOT, H2O, and AutoKeras. In particular, we study the influence of dirty data on accuracy, and consider how using dirty training data may help create more robust solutions. Furthermore, we also analyze how the structure of the generated pipelines differs in different cases.
Multiple testing for signal-agnostic searches of new physics with machine learning
NSF AI Institute for Artificial Intelligence and Fundamental Interactions（NSF人工智能与基础相互作用AI研究所）；MIT Laboratory for Nuclear Science（麻省理工学院核科学实验室）；School of Engineering and Applied Sciences, Harvard University（哈佛大学工程与应用科学学院）；University of Genoa（热那亚大学）；INFN, Sezione di Genova（意大利核物理研究所热那亚分所）
本文研究利用多重检验策略增强机器学习中的信号不可知搜索，通过结合不同超参数的检验并聚合 p 值或统计量，在避免模型偏差的同时实现与最佳检验相当且对异常响应更均匀的性能。
