[introductory/intermediate] Recommender Systems
Research in the field of recommender systems (recsys) has been very active in recent years. Recsys are embedded in a lot of daily activities and are considered to be a very challenging machine learning problem. Although machine learning has been profoundly impacted by deep learning, its impact on recommender systems was slow and not significant until recently. In this course we first introduce recsys, their challenges, tasks, domains, and classic approaches. We will then discuss the reasons to use deep learning algorithms for recsys and explore the application of a variety of deep learning models for common recsys challenges. Finally, we will deep dive into some specific recsys tasks and domains that utilize deep learning. This includes context-aware recommender systems, session-based recommendations, bundle recommendations, etc. Finally, we will discuss recent advances and future directions.
- Introduction to recommender systems – classic approaches.
- Deep learning for recommender systems – challenges and opportunities.
- Use cases – deep dive on specific recommender systems’ tasks and domains.
- Recent advances and outlook to future research directions.
Covington, Paul, Jay Adams, and Emre Sargin. “Deep neural networks for youtube recommendations.” In Proceedings of the 10th ACM Conference on Recommender Systems, pp. 191-198. 2016.
Eden, Sagi, Amit Livne, Oren Sar Shalom, Bracha Shapira, and Dietmar Jannach. “Investigating the Value of Subtitles for Improved Movie Recommendations.” In Proceedings of the 30th ACM Conference on User Modeling, Adaptation and Personalization (UMAP ’22). Association for Computing Machinery, New York, NY, USA, pp. 99–109. 2022. https://doi.org/10.1145/3503252.3531291
Livne, Amit, Moshe Unger, Bracha Shapira, and Lior Rokach. “Deep context-aware recommender system utilizing sequential latent context.” arXiv:1909.03999 (2019).
Ricci, Francesco, Lior Rokach, and Bracha Shapira. “Recommender Systems: Techniques, Applications, and Challenges.” Recommender Systems Handbook (2022): 1-35.
Wang, Shoujin, Longbing Cao, Yan Wang, Quan Z. Sheng, Mehmet A. Orgun, and Defu Lian. “A survey on session-based recommender systems.” ACM Computing Surveys (CSUR) 54, no. 7 (2021): 1-38.
Zhang, Shuai, Lina Yao, Aixin Sun, and Yi Tay. “Deep learning based recommender system: A survey and new perspectives.” ACM Computing Surveys (CSUR) 52, no. 1 (2019): 1-38.
Cheng, Heng-Tze, Levent Koc, Jeremiah Harmsen, Tal Shaked, Tushar Chandra, Hrishi Aradhye, Glen Anderson et al. “Wide & deep learning for recommender systems.” In Proceedings of the 1st Workshop on Deep Learning for Recommender Systems, pp. 7-10. 2016.
Introductory machine learning. Basic knowledge of deep learning.
Bracha Shapira is a full professor at the Department of Software and Information Systems Engineering at Ben-Gurion University of the Negev in Israel, and served as the head of the department for 6 years. She works on application of machine learning to various domains and specifically to recommender systems. She studies various recommender systems algorithmic aspects, such as context aware recommenders, bundle recommendations, evaluation aspects, explanability and more. She has published about 250 papers in journals and peer-reviewed conferences and registered several patents. She co-edited the popular Handbook of Recommender Systems (now 3rd edition). She regularly takes roles in leading conferences, such as PC chair at ACM Recsys 22, Doctoral Consortium chair at WSDM 2021, and Area chair at ACL 2019. Bracha collaborates with industry – she led numerous research projects at the Deutsche Telekom Lab at BGU and was the head of AI at a startup company (Sparks-AB).