- Conference Chairs:
- Yuriy Brun,
- Brittany Johnson,
- Alexandra Meliou
Modern software is full of examples of bias. FairWare 2018, the IEEE/ACM International Workshop on Software Fairness, brings together academics, practitioners, and policy makers interested in solving this problem and creating software engineering technology to improve software fairness. FairWare 2018 connects a variety of topics pertaining to software fairness, including surveys of real-world software exhibiting bias, definitions of measures of bias in software, approaches to detecting bias in software, standards for software fairness, and research challenges and roadmaps.
The central goal of FairWare 2018 is to stimulate research on the software engineering and system building sides of the fairness problem, complementing recent work the machine learning [1, 4--7] and theoretical [2] sides of the problem. Recent work [3] has identified some of the software engineering challenges of the problem, but more such challenges remain to be identified and solved, from fairness requirements elicitation and specification, to designing systems with fairness properties, to analysis and testing of fairness, to fairness maintenance. FairWare 2018 elevates these issues to the forefront in hopes of increasing research activity on this important problem.
Proceeding Downloads
Fairness definitions explained
Algorithm fairness has started to attract the attention of researchers in AI, Software Engineering and Law communities, with more than twenty different notions of fairness proposed in the last few years. Yet, there is no clear agreement on which ...
Integrating social values into software design patterns
Software Design Patterns (SDPs) are core solutions to the recurring problems in software. However, adopting SDPs without taking into account their value implications may result in breach of social values and ultimately lead to user dissatisfaction, lack ...
A roadmap for ethics-aware software engineering
Today's software is highly intertwined with our lives, and it possesses an increasing ability to act and influence us. Besides the renown example of self-driving cars and their potential harmfulness, more mundane software such as social networks can ...
Model-based discrimination analysis: a position paper
Decision-making software may exhibit biases due to hidden dependencies between protected characteristics and the data used as input for making decisions. To uncover such dependencies, we propose the development of a framework to support discrimination ...
On fairness in continuous electronic markets
Most of the world's financial markets are electronic (i.e., are implemented as software systems) and continuous (i.e., process orders received from market participants immediately, on a FIFO basis). In this short position paper I argue that such markets ...
Avoiding the intrinsic unfairness of the trolley problem
As an envisaged future of transportation, self-driving cars are being discussed from various perspectives, including social, economical, engineering, computer science, design, and ethical aspects. On the one hand, self-driving cars present new ...
IEEE P7003™ standard for algorithmic bias considerations: work in progress paper
The IEEE P7003 Standard for Algorithmic Bias Considerations is one of eleven IEEE ethics related standards currently under development as part of the IEEE Global Initiative on Ethics of Autonomous and Intelligent Systems. The purpose of the IEEE P7003 ...