Seminars and Events
Responsible recommendation system through the lens of conformal prediction and causal inference
Event Details
SPEAKER: Ruocheng Guo, ByteDance Research
Host: Fred Morstatter POC: Maura Covaci
REMINDER:
Meeting hosts only admit guests that they know to the Zoom meeting. Hence, you’re highly encouraged to use your USC account to sign into Zoom.
If you’re an outside visitor who has not yet subscribed to our series, please send an email to ([email protected]) with your Full Name, Title and Professional Affiliation at least 24 hours prior to the scheduled talk, so we can admit you from the Wait Room.
In-person attendance will be permitted for USC/ISI faculty, staff, students only. Open to the public virtually via the zoom link.
Visit links below to subscribe and for details on upcoming seminars:
https://www.isi.edu/isi-seminar-series/
Recommendation systems play a crucial role in today’s massive information systems. Unfortunately, existing methods developed for maximizing utility of recommendation systems will lead to issues such as unfair item exposure allocation and popularity bias. In this talk, I will discuss two of our recent works. In the first work, we propose an efficient method for fairness utility trade-off in ranking, which transforms deterministic rankers to stochastic ones with finite-sample utility guarantees and improved fairness. In the second work, we formulate debiasing recommendation system as a multiple causal inference problem, and handle confounding bias by learning identifiable latent confounders.
Speaker Bio
Ruocheng Guo is a Research Scientist at ByteDance Research in London, UK. His main research interest is responsible AI, causal inference and conformal prediction. He obtained Ph.D. degree with an outstanding Ph.D. student award from Arizona State University, where he was advised by Huan Liu. He was an assistant professor at City University of Hong Kong, an AI resident at Google X, and a research intern at Microsoft Research and Etsy.