Part I: Introduction and Background
30 minutes- Problem definitions and settings
- Key challenges
- Applications and use cases
Continual Recommender Systems
CIKM 2025 · November 10, 2025
CIKM 2025
Continual Recommender Systems
November 10, 2025Half day · Approximately 3 hours including short breaks
Abstract
Modern recommender systems operate in uniquely dynamic settings: user interests, item pools, and popularity trends shift continuously, and models must adapt in real time without forgetting past preferences.
While existing tutorials on continual or lifelong learning cover broad machine learning domains such as vision and graphs, they do not address recommendation-specific demands—such as balancing stability and plasticity per user, handling cold-start items, and optimizing recommendation metrics under streaming feedback. This tutorial aims to make a timely contribution by filling that gap.
We begin by reviewing the background and problem settings, followed by a comprehensive overview of existing approaches, including replay-based and regularization-based methods. We then highlight recent efforts to apply continual learning to practical deployment environments, such as resource-constrained systems and sequential interaction settings. Finally, we discuss open challenges and future research directions.
We believe this tutorial will be valuable to researchers and practitioners in recommender systems, data mining, and artificial intelligence, and will benefit a wide range of real-world application domains related to information retrieval.
Outline and Timeline
Half day · Approximately 3 hours including short breaksPart II: Experience-Replay-based Methods
35 minutes- Sample selection for experience replay
- Replay-based model enhancement
Part III: Regularization-based Methods
35 minutes- What knowledge to regularize
- Which temporal knowledge to regularize
- Personalization of regularization
Part IV: Beyond Traditional Settings
35 minutes- Resource-constrained environments
- Lifelong sequential environments
- Federated learning environments
Part V: Open Challenges and Future Directions
35 minutes- Generative recommendation with LLMs
- Trustworthiness
- Adaptation to foundational models
Speakers
Hyunsik Yoo
Hyunsik Yoo is a fourth-year Ph.D. student in the Siebel School of Computing and Data Science at the University of Illinois Urbana-Champaign. His research focuses on developing data mining and machine learning techniques for recommender systems and graph mining models that are adaptive, trustworthy, and user-inclusive.
His work has been published in major conferences, including KDD, SIGIR, TheWebConf, WSDM, and ICML. He has also served as a program committee member or reviewer for venues such as KDD, CIKM, TheWebConf Companion, AAAI, NeurIPS, DSAA, and TIST.
SeongKu Kang
SeongKu Kang is an Assistant Professor in the Department of Computer Science and Engineering at Korea University. Prior to that, he was a postdoctoral researcher at the University of Illinois Urbana-Champaign. His research interests lie in data mining, recommender systems, and information retrieval.
He has published more than 30 papers in major conferences such as KDD, TheWebConf, CIKM, SIGIR, and EMNLP. He received the Stars of Tomorrow Award from Microsoft Research Asia in 2023, and his paper was selected as a Best Paper at WSDM 2025. He was also recognized as an outstanding reviewer at KDD.
Hanghang Tong
Hanghang Tong is a professor in the Siebel School of Computing and Data Science at the University of Illinois Urbana-Champaign. Before that he was an associate professor at Arizona State University. He received his M.Sc. and Ph.D. degrees from Carnegie Mellon University in 2008 and 2009, both in Machine Learning. His research interest is in large-scale data mining for graphs and multimedia.
He has received several awards, including the IEEE ICDM Tao Li Award, SDM/IBM Early Career Data Mining Research Award, NSF CAREER Award, ICDM 10-Year Highest Impact Paper Awards, and several best paper awards. He has published over 300 refereed articles and is a distinguished member of ACM and a Fellow of IEEE.
References
13 worksThis list includes the prior works covered in this tutorial.
- Ahrabian, K., Xu, Y., Zhang, Y., Wu, J., Wang, Y., & Coates, M. (2021). Structure aware experience replay for incremental learning in graph-based recommender systems. CIKM 2021, 2832–2836.
- Mi, F., Lin, X., & Faltings, B. (2020). Ader: Adaptively distilled exemplar replay towards continual learning for session-based recommendation. RecSys 2020, 408–413.
- Cai, G., Zhu, J., Dai, Q., Dong, Z., He, X., Tang, R., & Zhang, R. (2022). Reloop: A self-correction continual learning loop for recommender systems. SIGIR 2022, 2692–2697.
- Zhu, J., Cai, G., Huang, J., Dong, Z., Tang, R., & Zhang, W. (2023). ReLoop2: Building Self-Adaptive Recommendation Models via Responsive Error Compensation Loop. KDD 2023, 5728–5738.
- Zhang, X., Chen, Y., Ma, C., Fang, Y., & King, I. (2024). Influential exemplar replay for incremental learning in recommender systems. AAAI 2024, 9368–9376.
- Qin, J., Liu, W., Zhang, W., & Yu, Y. (2025). D2K: Turning historical data into retrievable knowledge for recommender systems. TheWebConf 2025, 472–482.
- Wang, Y., Zhang, Y., Valkanas, A., Tang, R., Ma, C., Hao, J., & Coates, M. (2023). Structure aware incremental learning with personalized imitation weights for recommender systems. AAAI 2023, 4711–4719.
- Xu, Y., et al. (2020). GraphSAIL: Graph structure aware incremental learning for recommender systems. CIKM 2020.
- Wang, Y., Zhang, Y., & Coates, M. (2021). Graph structure aware contrastive knowledge distillation for incremental learning in recommender systems. CIKM 2021, 3518–3522.
- Yoo, H., Kang, S., Qiu, R., Xu, C., Wang, F., & Tong, H. (2025). Embracing plasticity: Balancing stability and plasticity in continual recommender systems. SIGIR 2025.
- Lee, G., Kang, S., Kweon, W., & Yu, H. (2024). Continual Collaborative Distillation for Recommender System. KDD 2024, 1495–1505.
- Lee, G., Yoo, H., Hwang, J., Kang, S., & Yu, H. (2025). Leveraging Historical and Current Interests for Continual Sequential Recommendation. arXiv:2506.07466.
- Liu, L., Cai, L., Zhang, C., Zhao, X., Gao, J., Wang, W., et al. (2023). LinRec: Linear attention mechanism for long-term sequential recommender systems. SIGIR 2023, 289–299.