• 14:00-14:50 Opening and Keynote by Prof. Mobasher – Adapting to User Preference Changes in Interactive Recommendation

Session 1

  • 14:50-15:10 Do Better ImageNet Models Transfer Better … for Image Recommendation?
  • 15:10-15:30 A Hybrid Variational Autoencoder for Collaborative Filtering
    • Kilol Gupta, Mukund Yelahanka Raghuprasad and Pankhuri Kumar
    • Link to paper

15:30-16:00 Coffee Break

16:00-17:30 Session 2

  • 16:00-16:30 Inferring Complementary Products from Baskets and Browsing Sessions
  • 16:30-17:00 A novel approach for venue recommendation using cross-domain techniques
  • 17:00-17:30 Detecting Changes in User Preferences using Hidden Markov Models for Sequential Recommendation Tasks

Keynote by: Prof. Bamshad Mobasher

Title: Adapting to User Preference Changes in Interactive Recommendation


Personalized recommender systems have become essential tools to alleviate information overload by tailoring their recommendations to users’ overall personal preferences. In many domains, however, the tastes and preferences of users change over time due to a variety of factors including changes in context, the task at hand, or even because of a general evolution of user’s interests. Recommender systems should capture these dynamics in user preferences in order to remain tuned to a user’s needs over time. In this talk I will focus on the problem of modeling and adapting to changes in user preferences. Specifically, I will discuss several recommendation approaches for modeling a user’s “interactional context,” where context is not directly represented using a pre specified set of explicit variables, but is inferred based on observations of changes in users’ behaviors in the course of their ongoing interactions with the system. I will highlight the use of latent factor models as well as social or semantic knowledge as the basis for inferring contextual changes or changes in preference states. I will also describe an approach based on the multi-armed bandit strategy and change-point analysis in order to incrementally adapt recommendations to changes in user preferences.


Dr. Bamshad Mobasher is a Professor of Computer Science and the director of the Center for Web Intelligence at the School of Computing of DePaul University in Chicago. His research areas include Web mining, Web personalization, recommender systems, predictive user modeling, and information retrieval. He has published five edited books and about 200 scientific articles, including several seminal papers in Web mining and Web personalization that are among the most cited in these areas. He has served in senior leadership positions for numerous conferences, including ACM RecSys, Conference on User Modeling, Adaptation and Personalization (UMAP), and ACM Conference on Knowledge Discovery and Data Mining (KDD). As the director of the Center for Web Intelligence, Dr. Mobasher is directs research in recommender systems and intelligent information systems; and he oversees joint projects with industry. Dr. Mobasher serves as an associate editor for the ACM Transactions on the Web, the ACM Transactions on Intelligent Interactive Systems, and the ACM Transactions on Internet Technology. His has served on the editorial boards of several other prominent computing journals, including User Modeling and User-Adapted Interaction, and the Journal of Web Semantics.