Recommender Systems focus users on a small selection of items from a much larger catalog, alleviating information overload and boosting sales for Internet retailers. This tutorial aims to provide a comprehensive and in-depth exploration of the complexities involved in adapting language modeling paradigms to improve the performance and ethical considerations of recommender systems.
Understanding Language Modeling Paradigm Adaptations in Recommender Systems: Lessons Learned and Open Challenges
Lemei Zhang is a postdoctoral researcher at the Norwegian Re-search Center for AI Innovation (NorwAI) at NTNU, Norway. Her research topics include natural language processing, recommender systems, and user modeling. Specifically, she focuses on applying data mining and natural language processing techniques to design effective algorithms that enhance the performance of recommender systems in various domains. Her current research is focusing on the development of foundational language models and their application in recommender systems. Her research has appeared in TACL, TOIS, UMUAI, RecSys, ECML-PKDD, etc., and she actively serves as a PC member or reviewer for conferences and journals such as AAAI, ACM Computing Surveys, UMUAI, and TWEB.
Peng Liu is a postdoctoral researcher at the Norwegian Research Center for AI Innovation (NorwAI) at NTNU, Norway. His research focuses on the intersection of Natural Language Processing and Recommender Systems. His primary interests lie in the areas of language modeling, sentiment analysis, and recommendation algorithms based on data streams and multimodal contexts such as text and images. His research appears in TACL, NAACL, SIGIR, RecSys, TOIS, UMUAI, ECML-PKDD, etc., and he regularly serves as a PC member or reviewer for conferences and journals such as ACL, EMNLP, NAACL, IJCAI, AAAI, TKDE, TOIS, UMUAI, etc.
Yashar Deldjoo is a tenure-track Assistant Professor at the Poly- technic University of Bari, Italy. He earned his Ph.D. with distinction in recommender systems from the Polytechnic University of Milan, Italy’s best technical university. His main research is centered on the study and the development of recommender systems that are not only accurate but also “trustworthy”, and adhere to human norms and values. His work emphasizes model fairness, robustness, privacy, and interpretability. His recent research also studies the application of “Generative AI and LLMs” in Recommender Systems and ML applications [19, 5]. He has served as the lead author on three comprehensive survey papers for ACM CSUR [4, 6, 3], as well as on a notable survey on “fairness in recommender systems” for the UMUAI journal [5]. He regularly publishes at SIGIR, RecSys, ECIR, ECAI, CVPR, and journals, including CSUR, UMUAI, IP&M, TKDE, and TIST. He contributed two book chapters to the 3rd Edition of “Recommender Systems Handbook”, the best book in the RecSys community. He presented tutorials at IR/RSs venues, including WSDM, RecSys, and ECIR. Additionally, he plays an active role in the academic community, organizing notable workshops like the ACM RecSys Challenge and MediaEval, as well as IIR ’21.
Yong Zheng is an Assistant Professor at the Department of Information Technology and Management within the Illinois Institute of Technology, in the USA. His primary research focus lies in user modeling and recommender systems. He has contributed to various renowned conferences such as ACM RecSys, ACM UMAP, and ACM IUI as an organizing committee member. He has experience in delivering academic tutorials, such as his tutorials on topics like multi-criteria recommender systems at ACM IUI 2023, multi-objective recommender systems at ACM SIGKDD 2021, and multi-stakeholder recommender systems at ACM RecSys 2019, etc.
Jon Atle Gulla is a professor of information systems at the Norwegian University of Science and Technology since 2002 and the director of the Norwegian Research Center for AI Innovation. He has a Ph.D. in computer science from 1993 and holds three M.Sc. degrees in computer science, linguistics, and management. His research is on natural language processing and semantics in the context of recommender systems, search engines, and conversational systems. He has close to 150 international publications and has supervised around 70 MSc students, 30 PhDs and 10 Postdocs.