Description changed:
22 October 2019 12:00-13:00. Dr Styliani Kleanthous, Open University of Cyprus.
Information School level 3: Digital Media Lab rm 324.
"Fairness in Proprietary Image Tagging Algorithms".
Abstract
Image analysis algorithms have become indispensable in the modern information ecosystem. Beyond their early use in restricted domains (e.g., military, medical), they are now widely used in consumer applications and social media enabling functionality that users take for granted.
Recently image analysis algorithms, have become widely available as Cognitive Services. This practice is proving to be a boon to the development of applications where user modeling, personalization and adaptation are required. But while tagging APIs offer developers an inexpensive and convenient means to add functionality to their creations, most are opaque and proprietary and there are numerous social and ethical issues surrounding their use in contexts where people can be harmed. In this talk, I will discuss recent work in analyzing proprietary image tagging services (e.g., Clarifai, Google Vision, Amazon Rekognition) for their gender and racial biases when tagging images depicting people [1]. I will present our techniques for discrimination discovery in this domain, as well as our work on understanding user perceptions of fairness [2]. Finally, I will explore the sources of such biases, by comparing human versus machine descriptions of the same people images [3].
[1] Kyriakou, K., Barlas, P., Kleanthous, S., & Otterbacher, J. (2019, July). Fairness in Proprietary Image Tagging Algorithms: A Cross-Platform Audit on People Images. In Proceedings of the International AAAI Conference on Web and Social Media (Vol. 13, No. 01, pp. 313-322).
[2] Barlas, P., Kleanthous, S., Kyriakou, K., & Otterbacher, J. (2019, June). What Makes an Image Tagger Fair?. In Proceedings of the 27th ACM Conference on User Modeling, Adaptation and Personalization (pp. 95-103). ACM.
[3] Otterbacher J., Barlas, P., Kleanthous, S., Kyriakou, K. 2019.How Do We Talk About Other People? Group (Un)Fairness in Natural Language Image Descriptions. In Seventh AAAI Conference on Human Computation and Crowdsourcing (HCOMP).
Bio
Styliani Kleanthous Loizou (female, Ph.D., University of Leeds, UK) is a research scientist at the CyCAT, Open University of Cyprus as well as the Research Centre on Interactive Media, Smart Systems and Emerging Technologies (RISE). Styliani’s main research interests and expertise are concentrated in the area of User and Community Modeling, Personalization and Adaptive Systems. She specializes in exploiting psychological and social theories for modeling user preferences, for designing intelligent interaction and adaptive user support. She has published over 25 papers in journals and scientific conferences, co-organized a number of international workshops and has given numerous presentations. Since 2004 she has been involved in different UK and EU-funded research projects for establishing requirements, modeling users and providing adaptive support for collaboration, learning, medical data analysis and identifying innovation networks.
