09,24,2021

 An Empirical Comparison of Bias Reduction Methods on Real-World Problems in High-Stakes Policy Settings2021-05-13   ${\displaystyle \cong }$ Applications of machine learning (ML) to high-stakes policy settings -- such as education, criminal justice, healthcare, and social service delivery -- have grown rapidly in recent years, sparking important conversations about how to ensure fair outcomes from these systems. The machine learning research community has responded to this challenge with a wide array of proposed fairness-enhancing strategies for ML models, but despite the large number of methods that have been developed, little empirical work exists evaluating these methods in real-world settings. Here, we seek to fill this research gap by investigating the performance of several methods that operate at different points in the ML pipeline across four real-world public policy and social good problems. Across these problems, we find a wide degree of variability and inconsistency in the ability of many of these methods to improve model fairness, but post-processing by choosing group-specific score thresholds consistently removes disparities, with important implications for both the ML research community and practitioners deploying machine learning to inform consequential policy decisions. There is no trade-off: enforcing fairness can improve accuracy2020-11-05   ${\displaystyle \cong }$ One of the main barriers to the broader adoption of algorithmic fairness in machine learning is the trade-off between fairness and performance of ML models: many practitioners are unwilling to sacrifice the performance of their ML model for fairness. In this paper, we show that this trade-off may not be necessary. If the algorithmic biases in an ML model are due to sampling biases in the training data, then enforcing algorithmic fairness may improve the performance of the ML model on unbiased test data. We study conditions under which enforcing algorithmic fairness helps practitioners learn the Bayes decision rule for (unbiased) test data from biased training data. We also demonstrate the practical implications of our theoretical results in real-world ML tasks. Strategies and Principles of Distributed Machine Learning on Big Data2015-12-31   ${\displaystyle \cong }$ The rise of Big Data has led to new demands for Machine Learning (ML) systems to learn complex models with millions to billions of parameters, that promise adequate capacity to digest massive datasets and offer powerful predictive analytics thereupon. In order to run ML algorithms at such scales, on a distributed cluster with 10s to 1000s of machines, it is often the case that significant engineering efforts are required --- and one might fairly ask if such engineering truly falls within the domain of ML research or not. Taking the view that Big ML systems can benefit greatly from ML-rooted statistical and algorithmic insights --- and that ML researchers should therefore not shy away from such systems design --- we discuss a series of principles and strategies distilled from our recent efforts on industrial-scale ML solutions. These principles and strategies span a continuum from application, to engineering, and to theoretical research and development of Big ML systems and architectures, with the goal of understanding how to make them efficient, generally-applicable, and supported with convergence and scaling guarantees. They concern four key questions which traditionally receive little attention in ML research: How to distribute an ML program over a cluster? How to bridge ML computation with inter-machine communication? How to perform such communication? What should be communicated between machines? By exposing underlying statistical and algorithmic characteristics unique to ML programs but not typically seen in traditional computer programs, and by dissecting successful cases to reveal how we have harnessed these principles to design and develop both high-performance distributed ML software as well as general-purpose ML frameworks, we present opportunities for ML researchers and practitioners to further shape and grow the area that lies between ML and systems. Learning by Design: Structuring and Documenting the Human Choices in Machine Learning Development2021-05-03   ${\displaystyle \cong }$ The influence of machine learning (ML) is quickly spreading, and a number of recent technological innovations have applied ML as a central technology. However, ML development still requires a substantial amount of human expertise to be successful. The deliberation and expert judgment applied during ML development cannot be revisited or scrutinized if not properly documented, and this hinders the further adoption of ML technologies--especially in safety critical situations. In this paper, we present a method consisting of eight design questions, that outline the deliberation and normative choices going into creating a ML model. Our method affords several benefits, such as supporting critical assessment through methodological transparency, aiding in model debugging, and anchoring model explanations by committing to a pre hoc expectation of the model's behavior. We believe that our method can help ML practitioners structure and justify their choices and assumptions when developing ML models, and that it can help bridge a gap between those inside and outside the ML field in understanding how and why ML models are designed and developed the way they are. MLSys: The New Frontier of Machine Learning Systems2019-12-01   ${\displaystyle \cong }$ Machine learning (ML) techniques are enjoying rapidly increasing adoption. However, designing and implementing the systems that support ML models in real-world deployments remains a significant obstacle, in large part due to the radically different development and deployment profile of modern ML methods, and the range of practical concerns that come with broader adoption. We propose to foster a new systems machine learning research community at the intersection of the traditional systems and ML communities, focused on topics such as hardware systems for ML, software systems for ML, and ML optimized for metrics beyond predictive accuracy. To do this, we describe a new conference, MLSys, that explicitly targets research at the intersection of systems and machine learning with a program committee split evenly between experts in systems and ML, and an explicit focus on topics at the intersection of the two. Hidden Technical Debts for Fair Machine Learning in Financial Services2021-03-18   ${\displaystyle \cong }$ The recent advancements in machine learning (ML) have demonstrated the potential for providing a powerful solution to build complex prediction systems in a short time. However, in highly regulated industries, such as the financial technology (Fintech), people have raised concerns about the risk of ML systems discriminating against specific protected groups or individuals. To address these concerns, researchers have introduced various mathematical fairness metrics and bias mitigation algorithms. This paper discusses hidden technical debts and challenges of building fair ML systems in a production environment for Fintech. We explore various stages that require attention for fairness in the ML system development and deployment life cycle. To identify hidden technical debts that exist in building fair ML system for Fintech, we focus on key pipeline stages including data preparation, model development, system monitoring and integration in production. Our analysis shows that enforcing fairness for production-ready ML systems in Fintech requires specific engineering commitments at different stages of ML system life cycle. We also propose several initial starting points to mitigate these technical debts for deploying fair ML systems in production. Statistical inference for individual fairness2021-03-30   ${\displaystyle \cong }$ As we rely on machine learning (ML) models to make more consequential decisions, the issue of ML models perpetuating or even exacerbating undesirable historical biases (e.g., gender and racial biases) has come to the fore of the public's attention. In this paper, we focus on the problem of detecting violations of individual fairness in ML models. We formalize the problem as measuring the susceptibility of ML models against a form of adversarial attack and develop a suite of inference tools for the adversarial cost function. The tools allow auditors to assess the individual fairness of ML models in a statistically-principled way: form confidence intervals for the worst-case performance differential between similar individuals and test hypotheses of model fairness with (asymptotic) non-coverage/Type I error rate control. We demonstrate the utility of our tools in a real-world case study. A Rigorous Machine Learning Analysis Pipeline for Biomedical Binary Classification: Application in Pancreatic Cancer Nested Case-control Studies with Implications for Bias Assessments2020-09-08   ${\displaystyle \cong }$ Machine learning (ML) offers a collection of powerful approaches for detecting and modeling associations, often applied to data having a large number of features and/or complex associations. Currently, there are many tools to facilitate implementing custom ML analyses (e.g. scikit-learn). Interest is also increasing in automated ML packages, which can make it easier for non-experts to apply ML and have the potential to improve model performance. ML permeates most subfields of biomedical research with varying levels of rigor and correct usage. Tremendous opportunities offered by ML are frequently offset by the challenge of assembling comprehensive analysis pipelines, and the ease of ML misuse. In this work we have laid out and assembled a complete, rigorous ML analysis pipeline focused on binary classification (i.e. case/control prediction), and applied this pipeline to both simulated and real world data. At a high level, this 'automated' but customizable pipeline includes a) exploratory analysis, b) data cleaning and transformation, c) feature selection, d) model training with 9 established ML algorithms, each with hyperparameter optimization, and e) thorough evaluation, including appropriate metrics, statistical analyses, and novel visualizations. This pipeline organizes the many subtle complexities of ML pipeline assembly to illustrate best practices to avoid bias and ensure reproducibility. Additionally, this pipeline is the first to compare established ML algorithms to 'ExSTraCS', a rule-based ML algorithm with the unique capability of interpretably modeling heterogeneous patterns of association. While designed to be widely applicable we apply this pipeline to an epidemiological investigation of established and newly identified risk factors for pancreatic cancer to evaluate how different sources of bias might be handled by ML algorithms. On the Legal Compatibility of Fairness Definitions2019-11-25   ${\displaystyle \cong }$ Past literature has been effective in demonstrating ideological gaps in machine learning (ML) fairness definitions when considering their use in complex socio-technical systems. However, we go further to demonstrate that these definitions often misunderstand the legal concepts from which they purport to be inspired, and consequently inappropriately co-opt legal language. In this paper, we demonstrate examples of this misalignment and discuss the differences in ML terminology and their legal counterparts, as well as what both the legal and ML fairness communities can learn from these tensions. We focus this paper on U.S. anti-discrimination law since the ML fairness research community regularly references terms from this body of law. Individually Fair Gradient Boosting2021-03-30   ${\displaystyle \cong }$ We consider the task of enforcing individual fairness in gradient boosting. Gradient boosting is a popular method for machine learning from tabular data, which arise often in applications where algorithmic fairness is a concern. At a high level, our approach is a functional gradient descent on a (distributionally) robust loss function that encodes our intuition of algorithmic fairness for the ML task at hand. Unlike prior approaches to individual fairness that only work with smooth ML models, our approach also works with non-smooth models such as decision trees. We show that our algorithm converges globally and generalizes. We also demonstrate the efficacy of our algorithm on three ML problems susceptible to algorithmic bias. Declarative Machine Learning - A Classification of Basic Properties and Types2016-05-19   ${\displaystyle \cong }$ Declarative machine learning (ML) aims at the high-level specification of ML tasks or algorithms, and automatic generation of optimized execution plans from these specifications. The fundamental goal is to simplify the usage and/or development of ML algorithms, which is especially important in the context of large-scale computations. However, ML systems at different abstraction levels have emerged over time and accordingly there has been a controversy about the meaning of this general definition of declarative ML. Specification alternatives range from ML algorithms expressed in domain-specific languages (DSLs) with optimization for performance, to ML task (learning problem) specifications with optimization for performance and accuracy. We argue that these different types of declarative ML complement each other as they address different users (data scientists and end users). This paper makes an attempt to create a taxonomy for declarative ML, including a definition of essential basic properties and types of declarative ML. Along the way, we provide insights into implications of these properties. We also use this taxonomy to classify existing systems. Finally, we draw conclusions on defining appropriate benchmarks and specification languages for declarative ML. Challenges and Pitfalls of Machine Learning Evaluation and Benchmarking2019-06-25   ${\displaystyle \cong }$ An increasingly complex and diverse collection of Machine Learning (ML) models as well as hardware/software stacks, collectively referred to as "ML artifacts", are being proposed - leading to a diverse landscape of ML. These ML innovations proposed have outpaced researchers' ability to analyze, study and adapt them. This is exacerbated by the complicated and sometimes non-reproducible procedures for ML evaluation. A common practice of sharing ML artifacts is through repositories where artifact authors post ad-hoc code and some documentation, but often fail to reveal critical information for others to reproduce their results. This results in users' inability to compare with artifact authors' claims or adapt the model to his/her own use. This paper discusses common challenges and pitfalls of ML evaluation and benchmarking, which can be used as a guideline for ML model authors when sharing ML artifacts, and for system developers when benchmarking or designing ML systems. Insights into Performance Fitness and Error Metrics for Machine Learning2020-05-17   ${\displaystyle \cong }$ Machine learning (ML) is the field of training machines to achieve high level of cognition and perform human-like analysis. Since ML is a data-driven approach, it seemingly fits into our daily lives and operations as well as complex and interdisciplinary fields. With the rise of commercial, open-source and user-catered ML tools, a key question often arises whenever ML is applied to explore a phenomenon or a scenario: what constitutes a good ML model? Keeping in mind that a proper answer to this question depends on a variety of factors, this work presumes that a good ML model is one that optimally performs and best describes the phenomenon on hand. From this perspective, identifying proper assessment metrics to evaluate performance of ML models is not only necessary but is also warranted. As such, this paper examines a number of the most commonly-used performance fitness and error metrics for regression and classification algorithms, with emphasis on engineering applications. Reducing malicious use of synthetic media research: Considerations and potential release practices for machine learning2019-07-28   ${\displaystyle \cong }$ The aim of this paper is to facilitate nuanced discussion around research norms and practices to mitigate the harmful impacts of advances in machine learning (ML). We focus particularly on the use of ML to create "synthetic media" (e.g. to generate or manipulate audio, video, images, and text), and the question of what publication and release processes around such research might look like, though many of the considerations discussed will apply to ML research more broadly. We are not arguing for any specific approach on when or how research should be distributed, but instead try to lay out some useful tools, analogies, and options for thinking about these issues. We begin with some background on the idea that ML research might be misused in harmful ways, and why advances in synthetic media, in particular, are raising concerns. We then outline in more detail some of the different paths to harm from ML research, before reviewing research risk mitigation strategies in other fields and identifying components that seem most worth emulating in the ML and synthetic media research communities. Next, we outline some important dimensions of disagreement on these issues which risk polarizing conversations. Finally, we conclude with recommendations, suggesting that the machine learning community might benefit from: working with subject matter experts to increase understanding of the risk landscape and possible mitigation strategies; building a community and norms around understanding the impacts of ML research, e.g. through regular workshops at major conferences; and establishing institutions and systems to support release practices that would otherwise be onerous and error-prone. Machine Learning for Intelligent Optical Networks: A Comprehensive Survey2020-03-11   ${\displaystyle \cong }$ With the rapid development of Internet and communication systems, both in services and technologies, communication networks have been suffering increasing complexity. It is imperative to improve intelligence in communication network, and several aspects have been incorporating with Artificial Intelligence (AI) and Machine Learning (ML). Optical network, which plays an important role both in core and access network in communication networks, also faces great challenges of system complexity and the requirement of manual operations. To overcome the current limitations and address the issues of future optical networks, it is essential to deploy more intelligence capability to enable autonomous and exible network operations. ML techniques are proved to have superiority on solving complex problems; and thus recently, ML techniques have been used for many optical network applications. In this paper, a detailed survey of existing applications of ML for intelligent optical networks is presented. The applications of ML are classified in terms of their use cases, which are categorized into optical network control and resource management, and optical networks monitoring and survivability. The use cases are analyzed and compared according to the used ML techniques. Besides, a tutorial for ML applications is provided from the aspects of the introduction of common ML algorithms, paradigms of ML, and motivations of applying ML. Lastly, challenges and possible solutions of ML application in optical networks are also discussed, which intends to inspire future innovations in leveraging ML to build intelligent optical networks. OmniFair: A Declarative System for Model-Agnostic Group Fairness in Machine Learning2021-03-12   ${\displaystyle \cong }$ Machine learning (ML) is increasingly being used to make decisions in our society. ML models, however, can be unfair to certain demographic groups (e.g., African Americans or females) according to various fairness metrics. Existing techniques for producing fair ML models either are limited to the type of fairness constraints they can handle (e.g., preprocessing) or require nontrivial modifications to downstream ML training algorithms (e.g., in-processing). We propose a declarative system OmniFair for supporting group fairness in ML. OmniFair features a declarative interface for users to specify desired group fairness constraints and supports all commonly used group fairness notions, including statistical parity, equalized odds, and predictive parity. OmniFair is also model-agnostic in the sense that it does not require modifications to a chosen ML algorithm. OmniFair also supports enforcing multiple user declared fairness constraints simultaneously while most previous techniques cannot. The algorithms in OmniFair maximize model accuracy while meeting the specified fairness constraints, and their efficiency is optimized based on the theoretically provable monotonicity property regarding the trade-off between accuracy and fairness that is unique to our system. We conduct experiments on commonly used datasets that exhibit bias against minority groups in the fairness literature. We show that OmniFair is more versatile than existing algorithmic fairness approaches in terms of both supported fairness constraints and downstream ML models. OmniFair reduces the accuracy loss by up to $94.8\%$ compared with the second best method. OmniFair also achieves similar running time to preprocessing methods, and is up to $270\times$ faster than in-processing methods. Towards a Robust and Trustworthy Machine Learning System Development2021-01-08   ${\displaystyle \cong }$ Machine Learning (ML) technologies have been widely adopted in many mission critical fields, such as cyber security, autonomous vehicle control, healthcare, etc. to support intelligent decision-making. While ML has demonstrated impressive performance over conventional methods in these applications, concerns arose with respect to system resilience against ML-specific security attacks and privacy breaches as well as the trust that users have in these systems. In this article, firstly we present our recent systematic and comprehensive survey on the state-of-the-art ML robustness and trustworthiness technologies from a security engineering perspective, which covers all aspects of secure ML system development including threat modeling, common offensive and defensive technologies, privacy-preserving machine learning, user trust in the context of machine learning, and empirical evaluation for ML model robustness. Secondly, we then push our studies forward above and beyond a survey by describing a metamodel we created that represents the body of knowledge in a standard and visualized way for ML practitioners. We further illustrate how to leverage the metamodel to guide a systematic threat analysis and security design process in a context of generic ML system development, which extends and scales up the classic process. Thirdly, we propose future research directions motivated by our findings to advance the development of robust and trustworthy ML systems. Our work differs from existing surveys in this area in that, to the best of our knowledge, it is the first of its kind of engineering effort to (i) explore the fundamental principles and best practices to support robust and trustworthy ML system development; and (ii) study the interplay of robustness and user trust in the context of ML systems. The Adversarial Machine Learning Conundrum: Can The Insecurity of ML Become The Achilles' Heel of Cognitive Networks?2019-06-03   ${\displaystyle \cong }$ The holy grail of networking is to create \textit{cognitive networks} that organize, manage, and drive themselves. Such a vision now seems attainable thanks in large part to the progress in the field of machine learning (ML), which has now already disrupted a number of industries and revolutionized practically all fields of research. But are the ML models foolproof and robust to security attacks to be in charge of managing the network? Unfortunately, many modern ML models are easily misled by simple and easily-crafted adversarial perturbations, which does not bode well for the future of ML-based cognitive networks unless ML vulnerabilities for the cognitive networking environment are identified, addressed, and fixed. The purpose of this article is to highlight the problem of insecure ML and to sensitize the readers to the danger of adversarial ML by showing how an easily-crafted adversarial ML example can compromise the operations of the cognitive self-driving network. In this paper, we demonstrate adversarial attacks on two simple yet representative cognitive networking applications (namely, intrusion detection and network traffic classification). We also provide some guidelines to design secure ML models for cognitive networks that are robust to adversarial attacks on the ML pipeline of cognitive networks. Local Interpretability of Calibrated Prediction Models: A Case of Type 2 Diabetes Mellitus Screening Test2020-06-02   ${\displaystyle \cong }$ Machine Learning (ML) models are often complex and difficult to interpret due to their 'black-box' characteristics. Interpretability of a ML model is usually defined as the degree to which a human can understand the cause of decisions reached by a ML model. Interpretability is of extremely high importance in many fields of healthcare due to high levels of risk related to decisions based on ML models. Calibration of the ML model outputs is another issue often overlooked in the application of ML models in practice. This paper represents an early work in examination of prediction model calibration impact on the interpretability of the results. We present a use case of a patient in diabetes screening prediction scenario and visualize results using three different techniques to demonstrate the differences between calibrated and uncalibrated regularized regression model. MLPerf Inference Benchmark2020-05-09   ${\displaystyle \cong }$ Machine-learning (ML) hardware and software system demand is burgeoning. Driven by ML applications, the number of different ML inference systems has exploded. Over 100 organizations are building ML inference chips, and the systems that incorporate existing models span at least three orders of magnitude in power consumption and five orders of magnitude in performance; they range from embedded devices to data-center solutions. Fueling the hardware are a dozen or more software frameworks and libraries. The myriad combinations of ML hardware and ML software make assessing ML-system performance in an architecture-neutral, representative, and reproducible manner challenging. There is a clear need for industry-wide standard ML benchmarking and evaluation criteria. MLPerf Inference answers that call. In this paper, we present our benchmarking method for evaluating ML inference systems. Driven by more than 30 organizations as well as more than 200 ML engineers and practitioners, MLPerf prescribes a set of rules and best practices to ensure comparability across systems with wildly differing architectures. The first call for submissions garnered more than 600 reproducible inference-performance measurements from 14 organizations, representing over 30 systems that showcase a wide range of capabilities. The submissions attest to the benchmark's flexibility and adaptability.