Roger Zhe Li
Roger Zhe Li has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Aghiles Salah
Huawei Ireland Research Center, Dublin, Ireland
3 shared publications - Barry Smyth
University College Dublin, Dublin, Ireland
3 shared publications - Changhong Jin
University College Dublin, Dublin, Ireland
3 shared publications - Mete Sertkan
Huawei Ireland Research Center, Dublin, Ireland
3 shared publications - Ruihai Dong
University College Dublin, Dublin, Ireland
3 shared publications - Dairui Liu
University College Dublin, Dublin, Ireland
2 shared publications
Latest Publications
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 9419-9423
IDs That Mean Something: A Hands-On Tutorial on Semantic IDs for Recommender Systems
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 9419-9423
Open AccessIDs That Mean Something: A Hands-On Tutorial on Semantic IDs for Recommender Systems
- Open Access
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 733-737
PriCoRec: A Privacy-Aware Cloud–Device Collaborative Framework for Ad Recommendation under Feature Constraints
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 733-737
Open AccessPriCoRec: A Privacy-Aware Cloud–Device Collaborative Framework for Ad Recommendation under Feature Constraints
- Open Access
- 24 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 241-252
RAMP: Robust Ad Recommendation Under Limited Personalized-Feature Availability via Masking and Alignment Pathways
- 24 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 241-252
Open AccessRAMP: Robust Ad Recommendation Under Limited Personalized-Feature Availability via Masking and Alignment Pathways
- Open Access
- 9 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 135-142
Mitigating Mainstream Bias in Recommendation via Cost-sensitive Learning
Mainstream bias, where some users receive poor recommendations because their preferences are uncommon or simply because they are less active, is an important aspect to consider regarding fairness in recommender systems. Existing methods to mitigate mainstream bias do not explicitly model the importance of these non-mainstream users or, when they do, it is in a way that is not necessarily compatible with the data and recommendation model at hand. In contrast, we use the recommendation utility as a more generic and implicit proxy to quantify mainstreamness, and propose a simple user-weighting approach to incorporate it into the training process while taking the cost of potential recommendation errors into account. We provide extensive experimental results showing that quantifying mainstreamness via utility is better able at identifying non-mainstream users, and that they are indeed better served when training the model in a cost-sensitive way. This is achieved with negligible or no loss in overall recommendation accuracy, meaning that the models learn a better balance across users. In addition, we show that research of this kind, which evaluates recommendation quality at the individual user level, may not be reliable if not using enough interactions when assessing model performance.
- 9 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 135-142
Open AccessMitigating Mainstream Bias in Recommendation via Cost-sensitive Learning
Mainstream bias, where some users receive poor recommendations because their preferences are uncommon or simply because they are less active, is an important aspect to consider regarding fairness in recommender systems. Existing methods to mitigate mainstream bias do not explicitly model the importance of these non-mainstream users or, when they do, it is in a way that is not necessarily compatible with the data and recommendation model at hand. In contrast, we use the recommendation utility as a more generic and implicit proxy to quantify mainstreamness, and propose a simple user-weighting approach to incorporate it into the training process while taking the cost of potential recommendation errors into account. We provide extensive experimental results showing that quantifying mainstreamness via utility is better able at identifying non-mainstream users, and that they are indeed better served when training the model in a cost-sensitive way. This is achieved with negligible or no loss in overall recommendation accuracy, meaning that the models learn a better balance across users. In addition, we show that research of this kind, which evaluates recommendation quality at the individual user level, may not be reliable if not using enough interactions when assessing model performance.
- Open Access
- 27 September 2018
- Published by Association for Computing Machinery (ACM)
- p. 553-557
Towards the next generation of multi-criteria recommender systems
- 27 September 2018
- Published by Association for Computing Machinery (ACM)
- p. 553-557
Open AccessTowards the next generation of multi-criteria recommender systems
- 1 October 2017
- Published by Elsevier in Journal of Systems and Software
- Vol. 132, 272-282
Adaptive Ensemble Undersampling-Boost: A novel learning framework for imbalanced data
- 1 October 2017
- Published by Elsevier in Journal of Systems and Software
- Vol. 132, 272-282
Adaptive Ensemble Undersampling-Boost: A novel learning framework for imbalanced data
- 1 April 2017
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 83, 157-165
A novel computer-aided diagnosis system for breast MRI based on feature selection and ensemble learning
- 1 April 2017
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 83, 157-165
A novel computer-aided diagnosis system for breast MRI based on feature selection and ensemble learning
- 1 December 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 122-127
MH-ARM: A Multi-Mode and High-Value Association Rule Mining Technique for Healthcare Data Analysis
The association rules mining process enables the end users to analyze, understand, and use the extracted knowledge in an intelligent system or to support the decision-making processes. To find valuable association rules from a large number of redundant rules, this paper proposes a deeper mining process, multi-mode and high value association rules mining (MH-ARM). This method takes into account the category information, the size of the item set, natural semantics, various metrics, and effective visualization of results. The process can effectively reduce the number of rules and improve the value and accuracy of the rules screened out for auxiliary diagnosis. In the end, the experimental data of rhinitis were analyzed and the effectiveness of the process was verified.
- 1 December 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 122-127
MH-ARM: A Multi-Mode and High-Value Association Rule Mining Technique for Healthcare Data Analysis
The association rules mining process enables the end users to analyze, understand, and use the extracted knowledge in an intelligent system or to support the decision-making processes. To find valuable association rules from a large number of redundant rules, this paper proposes a deeper mining process, multi-mode and high value association rules mining (MH-ARM). This method takes into account the category information, the size of the item set, natural semantics, various metrics, and effective visualization of results. The process can effectively reduce the number of rules and improve the value and accuracy of the rules screened out for auxiliary diagnosis. In the end, the experimental data of rhinitis were analyzed and the effectiveness of the process was verified.