Abstract: To truly bring everyone the inspiration to create a life they love, Pinterest is committed to content diversity and to developing inclusive search and recommendation engines. A top request we hear from Pinners is that they want to feel represented in the product. This is why we built the skin tone range and hair pattern technologies. These machine learning technologies are paving the way for more inclusive inspirations in Search and our augmented reality technology Try-On, and driving advances for more diverse recommendations across the platform. Developing inclusive AI in production requires an iterative and collaborative approach. We have learned the importance of building inclusive systems by design, of measuring to make progress, and of leveraging both artificial and human intelligence. We recognize that these challenges are multi-disciplinary, not just technical. In this talk, we describe sources of bias in ML for search and recommendation systems, techniques to mitigate bias, and production examples from our work at Pinterest to build inclusive search and recommendations.
Bio: Nadia Fawaz is a Senior Staff Applied Research Scientist and the Technical Lead for Inclusive AI at Pinterest. Her research and engineering interests include machine learning for personalization, AI fairness and data privacy, and her work aims at bridging theory and practice. She was named one of the 100 Brilliant Women in AI Ethics 2021, her work on Hair Pattern Search was recognized in the AI and Data category on Fast Company’s World Changing Ideas 2022 list with an honorable mention, and her work on inclusive AI was featured in many news outlets, including The Wall Street Journal, Fast Company, Vogue Business and CBS. She was a winner of the ACM RecSyS challenge on Context-Aware Movie Recommendations CAMRa2011 and her 2012 UAI paper was featured in an MIT TechReview article as “The Ultimate Challenge For Recommendation Engines”. Earlier, she was a Staff Software Engineer in Machine Learning and the Tech Lead for the job recommendation AI team at LinkedIn, a Principal Research Scientist at Technicolor Research lab, and a postdoctoral researcher at the Massachusetts Institute of Technology, Research Laboratory of Electronics. She received her Ph.D. in 2008 and her Diplome d'ingenieur (M.Sc.) in 2005 both in EECS from Telecom ParisTech and EURECOM, France. She is a member of the IEEE and of the ACM.