Xiquan Cui
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xiquan Cui has a total of 36 co-authors. Here are the top co-authors by number of shared publications:
- Vachik Dave
Walmart Global Tech, Sunnyvale, CA, USA
5 shared publications - Julian McAuley
University of California San Diego, La Jolla, USA
4 shared publications - Stephen Guo
Indeed, San Francisco, CA, USA
4 shared publications - Tao Ye
Lyft, San Francisco, CA, USA
4 shared publications - Chip Huyen
Claypot AI, San Francisco, California, USA
2 shared publications - Derek Zhiyuan Cheng
Google DeepMind, Mountain View, CA, USA
2 shared publications
Latest Publications
- Open Access
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 1858-1860
Online and Adaptive Recommender System
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 1858-1860
Open AccessOnline and Adaptive Recommender System
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 6268-6269
International Workshop on Online and Adaptive Recommender Systems (OARS 2025)
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 6268-6269
Open AccessInternational Workshop on Online and Adaptive Recommender Systems (OARS 2025)
- Open Access
- 21 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 5580-5583
International Workshop on Online and Adaptive Recommender Systems (OARS 2024)
- 21 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 5580-5583
Open AccessInternational Workshop on Online and Adaptive Recommender Systems (OARS 2024)
- Open Access
- 13 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 264-273
Knowledge Graph-based Session Recommendation with Session-Adaptive Propagation
Session-based recommender systems (SBRSs) predict users' next interacted items based on their historical activities. While most SBRSs capture purchasing intentions locally within each session, capturing items' global information across different sessions is crucial in characterizing their general properties. Previous works capture this cross-session information by constructing graphs and incorporating neighbor information. However, this incorporation cannot vary adaptively according to the unique intention of each session, and the constructed graphs consist of only one type of user-item interaction. To address these limitations, we propose knowledge graph-based session recommendation with session-adaptive propagation. Specifically, we build a knowledge graph by connecting items with multi-typed edges to characterize various user-item interactions. Then, we adaptively aggregate items' neighbor information considering user intention within the learned session. Experimental results demonstrate that equipping our constructed knowledge graph and session-adaptive propagation enhances session recommendation backbones by 10%-20%. Moreover, we provide an industrial case study showing our proposed framework achieves 2% performance boost over an existing well-deployed model at The Home Depot e-platform.
- 13 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 264-273
Open AccessKnowledge Graph-based Session Recommendation with Session-Adaptive Propagation
Session-based recommender systems (SBRSs) predict users' next interacted items based on their historical activities. While most SBRSs capture purchasing intentions locally within each session, capturing items' global information across different sessions is crucial in characterizing their general properties. Previous works capture this cross-session information by constructing graphs and incorporating neighbor information. However, this incorporation cannot vary adaptively according to the unique intention of each session, and the constructed graphs consist of only one type of user-item interaction. To address these limitations, we propose knowledge graph-based session recommendation with session-adaptive propagation. Specifically, we build a knowledge graph by connecting items with multi-typed edges to characterize various user-item interactions. Then, we adaptively aggregate items' neighbor information considering user intention within the learned session. Experimental results demonstrate that equipping our constructed knowledge graph and session-adaptive propagation enhances session recommendation backbones by 10%-20%. Moreover, we provide an industrial case study showing our proposed framework achieves 2% performance boost over an existing well-deployed model at The Home Depot e-platform.
- Open Access
- 4 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 1208-1209
The 3rd International Workshop on Interactive and Scalable Information Retrieval Methods for eCommerce (ISIR-eCom 2024)
Over the past few years, consumer behavior has shifted from traditional in-store shopping to online shopping. For example, eCommerce sales have grown from around 5% of total US sales in 2012 to around 15.4% in year 2023. This rapid growth of eCommerce has created new challenges and vital new requirements for intelligent information retrieval systems. Which lead to the primary motivations of this workshop: (1) Since the pandemic hit, eCommerce became an important part of people's routine and they started using online shop- ping for smallest grocery items to big electronics as well as cars. With such a large assortment of products and millions of users, achieving higher scalability without losing accuracy is a leading concern for information retrieval systems for eCommerce. (2) The diverse buyers make the relevance of the results highly subjective, because relevance varies for different buyers. The most suitable and intuitive solution to this problem is to make the system interactive and provide correct relevance for different users. Hence, interactive information retrieval systems are becoming necessity in eCommerce. (3) To handle sudden change in buyers' behavior, industries adopted existing sub-optimal information retrieval techniques for various eCommerce tasks. Parallelly, they also started exploring/researching for better solutions and in dire need of help from research community. This workshop will provide a forum to discuss and learn the latest trends for interactive and scalable information retrieval approaches for eCommerce. It will provide academic and industrial researchers a platform to present their latest works, share research ideas, present and discuss various challenges, and identify the areas where further research is needed. It will foster the development of a strong research community focused on solving eCommerce-related information retrieval problems that provide superior eCommerce experience to all users.
- 4 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 1208-1209
Open AccessThe 3rd International Workshop on Interactive and Scalable Information Retrieval Methods for eCommerce (ISIR-eCom 2024)
Over the past few years, consumer behavior has shifted from traditional in-store shopping to online shopping. For example, eCommerce sales have grown from around 5% of total US sales in 2012 to around 15.4% in year 2023. This rapid growth of eCommerce has created new challenges and vital new requirements for intelligent information retrieval systems. Which lead to the primary motivations of this workshop: (1) Since the pandemic hit, eCommerce became an important part of people's routine and they started using online shop- ping for smallest grocery items to big electronics as well as cars. With such a large assortment of products and millions of users, achieving higher scalability without losing accuracy is a leading concern for information retrieval systems for eCommerce. (2) The diverse buyers make the relevance of the results highly subjective, because relevance varies for different buyers. The most suitable and intuitive solution to this problem is to make the system interactive and provide correct relevance for different users. Hence, interactive information retrieval systems are becoming necessity in eCommerce. (3) To handle sudden change in buyers' behavior, industries adopted existing sub-optimal information retrieval techniques for various eCommerce tasks. Parallelly, they also started exploring/researching for better solutions and in dire need of help from research community. This workshop will provide a forum to discuss and learn the latest trends for interactive and scalable information retrieval approaches for eCommerce. It will provide academic and industrial researchers a platform to present their latest works, share research ideas, present and discuss various challenges, and identify the areas where further research is needed. It will foster the development of a strong research community focused on solving eCommerce-related information retrieval problems that provide superior eCommerce experience to all users.
- Open Access
- 4 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 3364-3375
Local Boosting for Weakly-Supervised Learning
Boosting is a commonly used technique to enhance the performance of a set of base models by combining them into a strong ensemble model. Though widely adopted, boosting is typically used in supervised learning where the data is labeled accurately. However, in weakly supervised learning, where most of the data is labeled through weak and noisy sources, it remains nontrivial to design effective boosting approaches. In this work, we show that the standard implementation of the convex combination of base learners can hardly work due to the presence of noisy labels. Instead, we propose LocalBoost, a novel framework for weakly-supervised boosting. LocalBoost iteratively boosts the ensemble model from two dimensions, i.e., intra-source and inter-source. The intra-source boosting introduces locality to the base learners and enables each base learner to focus on a particular feature regime by training new base learners on granularity-varying error regions. For the inter-source boosting, we leverage a conditional function to indicate the weak source where the sample is more likely to appear. To account for the weak labels, we further design an estimate-then-modify approach to compute the model weights. Experiments on seven datasets show that our method significantly outperforms vanilla boosting methods and other weakly-supervised methods.
- 4 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 3364-3375
Open AccessLocal Boosting for Weakly-Supervised Learning
Boosting is a commonly used technique to enhance the performance of a set of base models by combining them into a strong ensemble model. Though widely adopted, boosting is typically used in supervised learning where the data is labeled accurately. However, in weakly supervised learning, where most of the data is labeled through weak and noisy sources, it remains nontrivial to design effective boosting approaches. In this work, we show that the standard implementation of the convex combination of base learners can hardly work due to the presence of noisy labels. Instead, we propose LocalBoost, a novel framework for weakly-supervised boosting. LocalBoost iteratively boosts the ensemble model from two dimensions, i.e., intra-source and inter-source. The intra-source boosting introduces locality to the base learners and enables each base learner to focus on a particular feature regime by training new base learners on granularity-varying error regions. For the inter-source boosting, we leverage a conditional function to indicate the weak source where the sample is more likely to appear. To account for the weak labels, we further design an estimate-then-modify approach to compute the model weights. Experiments on seven datasets show that our method significantly outperforms vanilla boosting methods and other weakly-supervised methods.
- Open Access
- 4 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 5855-5856
3rd Workshop on Online and Adaptive Recommender Systems (OARS)
Recommender systems (RecSys) play important roles in helping users navigate, discover, and consume large and highly dynamic information. Today, many RecSys solutions deployed in the real world rely on categorical user-profiles and/or pre-calculated recommendation actions that stay static during a user session. However, recent trends suggest that RecSys need to model user intent in real time and constantly adapt to meet user needs at the moment or change user behavior in situ. There are three primary drivers for this emerging need of online adaptation. First, in order to meet the increasing demand for a better personalized experience, the personalization dimensions and space will grow larger and larger. It would not be feasible to pre-compute recommended actions for all personalization scenarios beyond a certain scale. Second, in many settings the system does not have user prior history to leverage. Estimating user intent in real time is the only feasible way to personalize. As various consumer privacy laws tighten, it is foreseeable that many businesses will reduce their reliance on static user profiles. Therefore, it makes the modeling of user intent in real time an important research topic. Third, a user's intent often changes within a session and between sessions, and user behavior could shift significantly during dramatic events. A RecSys should adapt in real time to meet user needs and be robust against distribution shifts. The online and adaptive recommender systems (OARS) workshop offers a focused discussion of the study and application of OARS, and will bring together an interdisciplinary community of researchers and practitioners from both industry and academia. KDD, as the premier data science conference, is an ideal venue to gather leaders in the field to further research into OARS and promote its adoption. This workshop is complementary to several sessions of the main conference (e.g., recommendation, reinforcement learning, etc.) and brings them together using a practical and focused application.
- 4 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 5855-5856
Open Access3rd Workshop on Online and Adaptive Recommender Systems (OARS)
Recommender systems (RecSys) play important roles in helping users navigate, discover, and consume large and highly dynamic information. Today, many RecSys solutions deployed in the real world rely on categorical user-profiles and/or pre-calculated recommendation actions that stay static during a user session. However, recent trends suggest that RecSys need to model user intent in real time and constantly adapt to meet user needs at the moment or change user behavior in situ. There are three primary drivers for this emerging need of online adaptation. First, in order to meet the increasing demand for a better personalized experience, the personalization dimensions and space will grow larger and larger. It would not be feasible to pre-compute recommended actions for all personalization scenarios beyond a certain scale. Second, in many settings the system does not have user prior history to leverage. Estimating user intent in real time is the only feasible way to personalize. As various consumer privacy laws tighten, it is foreseeable that many businesses will reduce their reliance on static user profiles. Therefore, it makes the modeling of user intent in real time an important research topic. Third, a user's intent often changes within a session and between sessions, and user behavior could shift significantly during dramatic events. A RecSys should adapt in real time to meet user needs and be robust against distribution shifts. The online and adaptive recommender systems (OARS) workshop offers a focused discussion of the study and application of OARS, and will bring together an interdisciplinary community of researchers and practitioners from both industry and academia. KDD, as the premier data science conference, is an ideal venue to gather leaders in the field to further research into OARS and promote its adoption. This workshop is complementary to several sessions of the main conference (e.g., recommendation, reinforcement learning, etc.) and brings them together using a practical and focused application.
- Open Access
- 30 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 850-853
The 2nd Workshop on Interactive and Scalable Information Retrieval Methods for eCommerce (ISIR-eCom)
- 30 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 850-853
Open AccessThe 2nd Workshop on Interactive and Scalable Information Retrieval Methods for eCommerce (ISIR-eCom)
- Open Access
- 30 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 920
Foreword for Workshop on Decision Making for Information Retrieval and Recommender Systems
- 30 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 920
Open AccessForeword for Workshop on Decision Making for Information Retrieval and Recommender Systems
- Open Access
- 11 October 2006
- Published by Optica Publishing Group in Optics Letters
- Vol. 31 (21) , 3161-3163
Slanted hole array beam profiler (SHArP)—a high-resolution portable beam profiler based on a linear aperture array
We demonstrate a novel high-resolution portable beam profiler based on a slanted linear array of small apertures, termed a slanted hole array beam profiler (SHArP). The apertures are directly fabricated on a metal-coated CMOS imaging sensor. With a single linear scan, the aperture array can establish a virtual grid of sampling points for beam profiling. With our prototype, we demonstrate beam profiling of Gaussian beams over an area of with a resolution of (compare with the CMOS pixel size of ). The resolution can be improved into the range of submicrometers by fabricating smaller apertures. The good correspondence between the measured and calculated beam profiles proves the fidelity of our new beam profiling scheme.- 11 October 2006
- Published by Optica Publishing Group in Optics Letters
- Vol. 31 (21) , 3161-3163
Open AccessSlanted hole array beam profiler (SHArP)—a high-resolution portable beam profiler based on a linear aperture array
We demonstrate a novel high-resolution portable beam profiler based on a slanted linear array of small apertures, termed a slanted hole array beam profiler (SHArP). The apertures are directly fabricated on a metal-coated CMOS imaging sensor. With a single linear scan, the aperture array can establish a virtual grid of sampling points for beam profiling. With our prototype, we demonstrate beam profiling of Gaussian beams over an area of with a resolution of (compare with the CMOS pixel size of ). The resolution can be improved into the range of submicrometers by fabricating smaller apertures. The good correspondence between the measured and calculated beam profiles proves the fidelity of our new beam profiling scheme.