ICDM 2025 Workshop on User Modeling and Recommendation (UMRec)

ICDM 2025 Workshop on User Modeling and Recommendation (UMRec)

User modeling and recommendation systems are fundamental to advancing AI, providing critical insights into dynamic user behaviors and enabling scalable personalization. Leveraging emerging technologies like large language models (LLMs) enhances our ability to understand complex user interactions and improves recommendation precision. Addressing challenges such as algorithmic bias, decision-making transparency, and ethical deployment is essential for maintaining societal trust. Ultimately, research in this field represents a synergy of technical innovation and responsible application, driving both academic progress and impactful real-world solutions.

Call for Papers

This workshop aims to advance research and innovation in user modeling and recommendation systems, emphasizing both foundational methodologies and emerging challenges. We seek contributions that address dynamic user behavior modeling, personalization at scale, and ethical deployment of AI-driven recommendations. Key themes include leveraging advancements like large language models (LLMs) to enhance user interaction understanding, mitigating biases in recommendation algorithms, and improving transparency in decision-making processes. Additionally, we encourage submissions exploring novel evaluation frameworks and real-world applications that balance technical innovation with societal trust. The workshop provides an invaluable forum for researchers to present the latest advancements in the rapidly evolving field of recommender systems. We welcome original submissions focusing on user modeling and recommendation.

Paper Submission

Please submit a paper (minimum 4 pages and maximum 8 pages in IEEE double-column format) through the online submission system.

Please refer to the ICDM regular submission requirement for more information at : https://www.cloud-conf.net/icdm2023/call-for-papers.html

Paper submission link: Click here

Important Dates

Keynote Speakers

Prof. Le Wu, Hefei University of Technology

Homepage: Homepage

Bio: Le Wu is a Professor in the School of Computer Science & Information Engineering. Her research focuses on data mining and knowledge discovery, user modeling, personalized recommendation, and causal inference for decision making. She has published numerous high-quality works in leading conferences such as NeurIPS, SIGIR, and KDD, and received several awards, including the Wu Wen Jun AI Excellent Young Scientist Award (2022), the CAST Young Talent Promotion Project (2021), and the SI SDM Best Paper Award (2015). Let us welcome Dr. Wu to deliver her keynote talk, entiled “Recent Advances on Generative Recommendation”.

Keynote Title: Recent Advances on Generative Recommendation

---

Prof. Harrie Oosterhuis, Radboud University

Homepage: Homepage

Bio: Harrie Oosterhuis is an assistant professor at the Data Science Group of the Institute of Computing and Information Sciences (iCIS) of the Radboud University. His research lies on the intersection of machine learning and information retrieval, it primarily concerns optimizing ranking systems and learning from user interactions on rankings. He obtained his PhD cum laude from the University of Amsterdam in 2020 for his thesis titled "Learning from user interactions with rankings: A unification of the field", which received an Andreas Bonn medal from the Genootschap ter bevordering van Natuur-, Genees- en Heelkunde in 2024. In recent years, he was a visiting researcher at Twitter and Google DeepMind. Some of his works received best paper awards at ECIR’19, SIGIR’21, WSDM’21 and ICTIR’22; he is a recipient of a 2021 Google Research Scholar Award, a 2023 Radboud Science Award, a 2024 ACM SIGIR Early Career Researcher Award and a 2022 NWO Veni Grant.

Keynote Title: Reliable Confidence Intervals for Information Retrieval Evaluation Using Generative A.I.

---

Dr. Rui Liu, StarPlan AI

Homepage: Homepage

Bio: Rui Liu is the Founder of StarPlan, an AI recruitment platform leveraging multi-agent systems to help startups hire top AI talent across Australia. With a PhD in Human–Computer Interaction (HCI) from the University of Melbourne, Rui combines expertise in human–AI collaboration with real-world recruitment challenges to design autonomous agents that make talent matching faster, smarter, and more adaptive. Through StarPlan’s MAS, Rui works closely with founders and engineers, orchestrating AI agents that source, evaluate, and match candidates—building high-performing teams that drive the future of AI innovation.

Keynote Title: Multi-Agent system, Design, Implementation and Evaluation

Workshop Program

IEEE ICDM 2025 UMRec Workshop Tentative Schedule

Day 2: Thursday, November 13, 2025

Time	Location	Session
8:20-9:00	Presidential Ballroom	Opening Ceremony
10:25-10:30	Statler B	Welcome Remarks of ICDM Workshop on User Modeling and Recommendation (UMRec)
10:30-10:50	Statler B	Keynote Talk 1 by Prof. Le Wu, Hefei University of Technology (Title: Recent Advances on Generative Recommendation)
10:50-11:10	Statler B	Keynote Talk 2 by Prof. Harrie Oosterhuis, Radboud University (Title: Reliable Confidence Intervals for Information Retrieval Evaluation Using Generative A.I.)
11:10-11:30	Statler B	Keynote Talk 3 by Dr. Rui Liu, StarPlan AI (Title: Multi-Agent system, Design, Implementation and Evaluation)
11:30-11:50	Statler B	Oral by Milad Sabouri, DePaul University (Title: Effectiveness of LLMs in Temporal User Profiling for Recommendation)
11:50-12:10	Statler B	Oral by Liping Zhang, Adobe (Title: UWM3R: Uncertainty-Weighted Multi-Intent Experts for Direct–Deep Multimodal Ranking)
12:10-12:30	Statler B	Oral by Anshuman Guha, Johns Hopkins University (Title: Token Optimized Indexing with Named Entity Extraction from Conversational Data Services)
12:30-13:30	Presidential Ballroom	Lunch
14:00-14:20	Statler B	Oral by Junyou He, JD.COM (Title: Adversarial Alignment and Disentanglement for Cross-Domain CTR Prediction with Domain-Encompassing Features)
14:20-14:40	Statler B	Oral by Xiaxin Yuan, University of Science and Technology of China (Title: SemiSL-RDC: Semi-Supervised Rating Distribution Calibration via Pivot User for Debiasing Recommendation Systems)
14:40-15:00	Statler B	Oral by Tianyu Xia, Beijing University of Chemical Technology (Title: Temporally-Aware Integration of Randomized Controlled Trials for Mitigating Hidden Confounding in Recommendations)
15:00-15:20	Statler B	Oral by Jorge Cristhian Chamby-Diaz, Samsung Eletronica da Amazonia Ltda (Title: User Ranking System using Pareto Optimality and Usage Time Metrics)
15:20-15:40	Statler B	Oral by Sepinood Haghighi, University of Windsor (Title: Aspect-Aware Sentiment Interaction Modeling with DeBERTa for Enhanced Review-Based Recommendations)
15:40-16:00	Statler B	Oral by Shuqi Qin, MatrixOrigin (Title: Adaptive Calibrated Doubly Robust Estimators for Debiased Recommendation)
16:00-16:30	Capital Terrace, Congressional	Coffee Break
17:00-18:00	Statler B	Poster Session

Organizers

Contact Information

• Email: icdm.umrec@outlook.com