Fairness is an increasingly important concern as machine learning models are used to support decision making in high-stakes applications such as mortgage lending, hiring, and prison sentencing. This paper introduces a new open source Python toolkit for algorithmic fairness, AI Fairness 360 (AIF360), released under an Apache v2.0 license (https://github.com/ibm/aif360). The main objectives of this toolkit are to help facilitate the transition of fairness research algorithms to use in an industrial setting and to provide a common framework for fairness researchers to share and evaluate algorithms.The package includes a comprehensive set of fairness metrics for datasets and models, explanations for these metrics, and algorithms to mitigate bias in datasets and models. It also includes an interactive Web experience (https://aif360.mybluemix.net) that provides a gentle introduction to the concepts and capabilities for line-of-business users, as well as extensive documentation, usage guidance, and industry-specific tutorials to enable data scientists and practitioners to incorporate the most appropriate tool for their problem into their work products. The architecture of the package has been engineered to conform to a standard paradigm used in data science, thereby further improving usability for practitioners. Such architectural design and abstractions enable researchers and developers to extend the toolkit with their new algorithms and improvements, and to use it for performance benchmarking. A built-in testing infrastructure maintains code quality.

Accuracy is an important concern for suppliers of artificial intelligence (AI) services, but considerations beyond accuracy, such as safety (which includes fairness and explainability), security, and provenance, are also critical elements to engender consumers' trust in a service. Many industries use transparent, standardized, but often not legally required documents called supplier's declarations of conformity (SDoCs) to describe the lineage of a product along with the safety and performance testing it has undergone. SDoCs may be considered multi-dimensional fact sheets that capture and quantify various aspects of the product and its development to make it worthy of consumers' trust. Inspired by this practice, we propose FactSheets to help increase trust in AI services. We envision such documents to contain purpose, performance, safety, security, and provenance information to be completed by AI service providers for examination by consumers. We suggest a comprehensive set of declaration items tailored to AI and provide examples for two fictitious AI services in the appendix of the paper. * A. Olteanu's work was done while at IBM Research. Author is currently affiliated with Microsoft Research.

No abstract

This paper presents a survey of recent research on sparsity-driven synthetic aperture radar (SAR) imaging.In particular, it reviews (i) analysis and synthesis-based sparse signal representation formulations for SAR image formation together with the associated imaging results; (ii) sparsity-based methods for wide-angle SAR imaging and anisotropy characterization; (iii) sparsity-based methods for joint imaging and autofocusing from data with phase errors; (iv) techniques for exploiting sparsity for SAR imaging of scenes containing moving objects, and (v) recent work on compressed sensing-based analysis and design of SAR sensing missions.

In recent years there has been an increasing trend in which data scientists and domain experts work together to tackle complex scientific questions. However, such collaborations often face challenges. In this paper, we aim to decipher this collaboration complexity through a semi-structured interview study with 22 interviewees from teams of bio-medical scientists collaborating with data scientists. In the analysis, we adopt the Olsons' four-dimensions framework proposed in Distance Matters to code interview transcripts. Our findings suggest that besides the glitches in the collaboration readiness, technology readiness, and coupling of work dimensions, the tensions that exist in the common ground building process influence the collaboration outcomes, and then persist in the actual collaboration process. In contrast to prior works' general account of building a high level of common ground, the breakdowns of content common ground together with the strengthen ofprocess common ground in this process is more beneficial for scientific discovery. We discuss why that is and what the design suggestions are, and conclude the paper with future directions and limitations.Mao and Wang, et al. models submitted by approximately 100 research groups worldwide and granted the top winner to a Data Science researcher team -Google's Deepmind's AlphaFold [15]. The success of these interdisciplinary collaborations is also appealing to Human-Computer Interaction (HCI) researchers and a few papers have been published in recent years (e.g., offline data hackathon for civic issues [41], or online data challenges such as in Kaggle.com [14]).However, besides these aforementioned success stories, there are also turbulences in these collaborations. Even in the case study reporting a successful offline data hackathon event, Hou and Wang [41] described a tension between the NPOs' expectations (domain experts) and the data volunteers' expectations (data scientists), which they described as a "dual goal" dilemma. In the more general open science and cyberinfrastructure contexts, tensions and challenges are not rarely seen, which have been attributed to the interdisciplinary nature of the team [94], related motivational factors [84] and cultural differences [9], the remote and cross-culture team structure [54,57], the data-centric practice [79], or the lack of technology and infrastructure support [66].These tensions are not new in the Computer-Supported Cooperative Work (CSCW) field. In their landmark paper, "Distance Matters", 20 years ago [65] Olson and Olson developed a coherent framework to describe a collaboration to be successful or not. It has four dimensions: Common Ground, Coupling of Work, Collaboration Readiness, and Technology Readiness. Though they were primarily looking at remote, not necessarily data-centric, scientific collaborations at that time (which they referred to collaboratories [103]), their framework has been proven to be effective in analyzing more general collaborations beyond the "remote" settings [43,64,[67][68][69].In t...

No abstract

Machine learning algorithms increasingly influence our decisions and interact with us in all parts of our daily lives. Therefore, just as we consider the safety of power plants, highways, and a variety of other engineered socio-technical systems, we must also take into account the safety of systems involving machine learning. Heretofore, the definition of safety has not been formalized in a machine learning context. In this article, we do so by defining machine learning safety in terms of risk, epistemic uncertainty, and the harm incurred by unwanted outcomes. We then use this definition to examine safety in all sorts of applications in cyber-physical systems, decision sciences, and data products. We find that the foundational principle of modern statistical machine learning, empirical risk minimization, is not always a sufficient objective. We discuss how four different categories of strategies for achieving safety in engineering, including inherently safe design, safety reserves, safe fail, and procedural safeguards can be mapped to a machine learning context. We then discuss example techniques that can be adopted in each category, such as considering interpretability and causality of predictive models, objective functions beyond expected prediction accuracy, human involvement for labeling difficult or rare examples, and user experience design of software and open data.

No abstract