Pan Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Pan Li has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
Alexander Tuzhilin
Stern School of Business, New York University, New York, New York 10012
4 shared publications- Alexander Tuzhilin
New York University
4 shared publications - Maofei Que
Alibaba Group, Hangzhou, China
3 shared publications - Zhuoran Zhuang
Alibaba Group, Hangzhou, China
3 shared publications - Mingyuan Tao
Alibaba Group, Hangzhou, Zhejiang, China
2 shared publications - Shui Liu
Alibaba Group, Hangzhou, China
2 shared publications
Latest Publications
- 1 December 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (12) , 7873-7886
A Dynamical System Model for Knowledge Evolution and Exploration of User Trajectories in Recommender Systems
- 1 December 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (12) , 7873-7886
A Dynamical System Model for Knowledge Evolution and Exploration of User Trajectories in Recommender Systems
- Open Access
- 22 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 154-158
AGP: Auto-Guided Prompt Refinement for Personalized Reranking in Recommender Systems
Reranking plays a critical role in recommendation systems by refining initial predictions to better reflect user preferences. While large language models (LLMs) have shown promise in enhancing reranking through contextual reasoning, they still rely heavily on manually crafted prompts—an approach that is both labor-intensive and difficult to scale. Although prompt optimization has been studied in domains like question answering and news recommendation, its adaptation to general item recommendation remains limited due to the unstructured and inconsistent nature of item metadata. To address these challenges, we propose Auto-Guided Prompt Refinement (AGP), a novel framework that automatically refines user profile generation prompts instead of reranking prompts directly. AGP leverages position-based feedback, which encodes item-level ranking misalignments, and introduces batched training with aggregated feedback to ensure robust and generalizable prompt updates. Experimental results on Amazon Movies & TV, Yelp, and Goodreads demonstrate AGP's effectiveness. With only 100 training users, AGP improves NDCG@10 by 5.61%, 2.46%, and 6.18% when reranking SASRec, and by 9.36%, 7.98%, and 20.68% when reranking LightGCN. These results highlight AGP's potential as a scalable, automated solution for LLM-based personalized reranking. Code: https://github.com/ChenMetanoia/AGP
- 22 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 154-158
Open AccessAGP: Auto-Guided Prompt Refinement for Personalized Reranking in Recommender Systems
Reranking plays a critical role in recommendation systems by refining initial predictions to better reflect user preferences. While large language models (LLMs) have shown promise in enhancing reranking through contextual reasoning, they still rely heavily on manually crafted prompts—an approach that is both labor-intensive and difficult to scale. Although prompt optimization has been studied in domains like question answering and news recommendation, its adaptation to general item recommendation remains limited due to the unstructured and inconsistent nature of item metadata. To address these challenges, we propose Auto-Guided Prompt Refinement (AGP), a novel framework that automatically refines user profile generation prompts instead of reranking prompts directly. AGP leverages position-based feedback, which encodes item-level ranking misalignments, and introduces batched training with aggregated feedback to ensure robust and generalizable prompt updates. Experimental results on Amazon Movies & TV, Yelp, and Goodreads demonstrate AGP's effectiveness. With only 100 training users, AGP improves NDCG@10 by 5.61%, 2.46%, and 6.18% when reranking SASRec, and by 9.36%, 7.98%, and 20.68% when reranking LightGCN. These results highlight AGP's potential as a scalable, automated solution for LLM-based personalized reranking. Code: https://github.com/ChenMetanoia/AGP
- Open Access
- 21 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 436-446
CoDA: A Context-Decoupled Hierarchical Agent with Reinforcement Learning
- 21 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 436-446
Open AccessCoDA: A Context-Decoupled Hierarchical Agent with Reinforcement Learning
- Open Access
- 21 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 416-425
APPNet: Automatic Feature Partitioning-Based Parameter Personalized Network for Conversion Prediction in E-commerce
- 21 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 416-425
Open AccessAPPNet: Automatic Feature Partitioning-Based Parameter Personalized Network for Conversion Prediction in E-commerce
- Open Access
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 2587-2591
NAM: A Normalization Attention Model for Personalized Product Search In Fliggy
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 2587-2591
Open AccessNAM: A Normalization Attention Model for Personalized Product Search In Fliggy
- 1 September 2024
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Information Systems Research
- Vol. 35 (3) , 1257-1273
When Variety Seeking Meets Unexpectedness: Incorporating Variety-Seeking Behaviors into Design of Unexpected Recommender Systems
In this paper, we study the consumers’ variety-seeking behavior in recommender system applications and propose a comprehensive framework to measure such behavior based on past consumption records. The effectiveness of the proposed framework is validated through user questionnaire studies conducted at Alibaba, where our constructed variety-seeking measures match well with consumers’ self-reported levels of their variety-seeking behaviors. We subsequently present a recommendation framework that combines the identified variety-seeking levels with unexpected recommender systems in the data mining literature to address consumers’ heterogenous desire for product variety, in which we provide more unexpected product recommendations to variety-seeking consumers and vice versa. Through off-line experiments on three different recommendation scenarios and a large-scale online controlled experiment at a major video-streaming platform, we demonstrate that those models following our recommendation framework significantly increase various business performance metrics and generate tangible economic impact for the company. Our findings lead to important managerial implications to better understand consumers’ variety-seeking behaviors and design recommender systems. As a result, the best performing model in our proposed frameworks is deployed by the company to serve all consumers on the video-streaming platform.
- 1 September 2024
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Information Systems Research
- Vol. 35 (3) , 1257-1273
When Variety Seeking Meets Unexpectedness: Incorporating Variety-Seeking Behaviors into Design of Unexpected Recommender Systems
In this paper, we study the consumers’ variety-seeking behavior in recommender system applications and propose a comprehensive framework to measure such behavior based on past consumption records. The effectiveness of the proposed framework is validated through user questionnaire studies conducted at Alibaba, where our constructed variety-seeking measures match well with consumers’ self-reported levels of their variety-seeking behaviors. We subsequently present a recommendation framework that combines the identified variety-seeking levels with unexpected recommender systems in the data mining literature to address consumers’ heterogenous desire for product variety, in which we provide more unexpected product recommendations to variety-seeking consumers and vice versa. Through off-line experiments on three different recommendation scenarios and a large-scale online controlled experiment at a major video-streaming platform, we demonstrate that those models following our recommendation framework significantly increase various business performance metrics and generate tangible economic impact for the company. Our findings lead to important managerial implications to better understand consumers’ variety-seeking behaviors and design recommender systems. As a result, the best performing model in our proposed frameworks is deployed by the company to serve all consumers on the video-streaming platform.
- 26 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. PP (10414347) , 1-13
Dual Contrastive Learning for Efficient Static Feature Representation in Sequential Recommendations
Static user and item features constitute important information to be taken into account in the recommendation process. However, as these features are usually sparse and of large-vocabulary, existing deep learning-based methods typically construct large tables of high-dimensional feature embeddings, which is inefficient in terms of memory storage and is computationally problematic. On the other hand, while product quantization-based methods have been proposed to compress latent embeddings, they usually come at the cost of compromising recommendation performance due to the restrictive expressive power, as feature correlations and user-item interactions are not properly captured in the compression process. To address these issues, we propose a novel Dual Contrastive Learning method to generate low-dimensional discrete static feature representations that significantly reduce memory storage and computational complexity, while simultaneously producing superior recommendation performance. Extensive offline experiments on three large-scale industrial datasets demonstrate that our proposed model significantly outperforms the selected baselines. In addition, we conducted an online A/B test at Alibaba and show that the proposed model significantly improves the average video streaming time, while reducing the size of the feature embedding table by 90% over the currently deployed system.
- 26 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. PP (10414347) , 1-13
Dual Contrastive Learning for Efficient Static Feature Representation in Sequential Recommendations
Static user and item features constitute important information to be taken into account in the recommendation process. However, as these features are usually sparse and of large-vocabulary, existing deep learning-based methods typically construct large tables of high-dimensional feature embeddings, which is inefficient in terms of memory storage and is computationally problematic. On the other hand, while product quantization-based methods have been proposed to compress latent embeddings, they usually come at the cost of compromising recommendation performance due to the restrictive expressive power, as feature correlations and user-item interactions are not properly captured in the compression process. To address these issues, we propose a novel Dual Contrastive Learning method to generate low-dimensional discrete static feature representations that significantly reduce memory storage and computational complexity, while simultaneously producing superior recommendation performance. Extensive offline experiments on three large-scale industrial datasets demonstrate that our proposed model significantly outperforms the selected baselines. In addition, we conducted an online A/B test at Alibaba and show that the proposed model significantly improves the average video streaming time, while reducing the size of the feature embedding table by 90% over the currently deployed system.
- Open Access
- 9 November 2022
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
- Vol. 14 (1) , 1-25
Adversarial Learning for Cross Domain Recommendations
Existing cross domain recommender systems typically assume homogeneous user preferences across multiple domains to capture similarities of user-item interactions and to provide cross domain recommendations accordingly. Meanwhile, the heterogeneity of user behaviors is usually not well studied and captured during the recommendation process, where users might have vastly different interests in different domains. In addition, previous models focus primarily on recommendation tasks between domain pairs, and cannot be naturally extended to serve for multiple domain recommendation applications. To address these challenges, we propose to utilize the idea of adversarial learning to intelligently incorporate global user preferences and domain-specific user preferences for providing satisfying cross domain recommendations. In particular, our proposed Adversarial Cross Domain Recommendation (ACDR) model first obtains the latent representations of global user preferences from their explicit feature information, and then transforms them into domain-specific user embeddings, where we take into account user behaviors and their heterogeneous preferences among different domains. By doing so, we address the differences among user representations in the domain-specific latent space while also preserving global user preferences, as we effectively segment the distributions of domain-specific user embeddings in the shared latent space. The convergence of our proposed model is theoretically guaranteed. The proposed ACDR model leads to significant and consistent improvements in cross domain recommendation performance over the state-of-the-art baseline models, which we demonstrate through extensive experiments on three real-world datasets. In addition, we show that the improvements are greater on those datasets that are smaller and more sparse, on those users that have fewer interaction records in the dataset, and when user interactions from more product domains are included in the cross domain recommendation model.
- 9 November 2022
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
- Vol. 14 (1) , 1-25
Open AccessAdversarial Learning for Cross Domain Recommendations
Existing cross domain recommender systems typically assume homogeneous user preferences across multiple domains to capture similarities of user-item interactions and to provide cross domain recommendations accordingly. Meanwhile, the heterogeneity of user behaviors is usually not well studied and captured during the recommendation process, where users might have vastly different interests in different domains. In addition, previous models focus primarily on recommendation tasks between domain pairs, and cannot be naturally extended to serve for multiple domain recommendation applications. To address these challenges, we propose to utilize the idea of adversarial learning to intelligently incorporate global user preferences and domain-specific user preferences for providing satisfying cross domain recommendations. In particular, our proposed Adversarial Cross Domain Recommendation (ACDR) model first obtains the latent representations of global user preferences from their explicit feature information, and then transforms them into domain-specific user embeddings, where we take into account user behaviors and their heterogeneous preferences among different domains. By doing so, we address the differences among user representations in the domain-specific latent space while also preserving global user preferences, as we effectively segment the distributions of domain-specific user embeddings in the shared latent space. The convergence of our proposed model is theoretically guaranteed. The proposed ACDR model leads to significant and consistent improvements in cross domain recommendation performance over the state-of-the-art baseline models, which we demonstrate through extensive experiments on three real-world datasets. In addition, we show that the improvements are greater on those datasets that are smaller and more sparse, on those users that have fewer interaction records in the dataset, and when user interactions from more product domains are included in the cross domain recommendation model.
- 13 October 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 34 (8) , 3854-3866
Learning Latent Multi-Criteria Ratings From User Reviews for Recommendations
Multi-criteria recommender systems have been increasingly useful for helping consumers identify the most relevant items based on different dimensions of user experiences and highlighting their most valued features. Therefore, researchers have proposed various multi-criteria models to improve recommendation performance. However, most of the existing methods utilize only multi-criteria ratings explicitly provided by the users. Note that explicit multi-criteria ratings are sparse and have the problem of missing values. User reviews, on the other hand, contain richer information of user experiences and reveal multi-dimensional user preferences. Therefore, we propose to use latent multi-criteria ratings generated from user reviews, as opposed to explicit multi-criteria ratings, to provide recommendations and capture latent complex heterogeneous user preferences. Specifically, we propose two novel models for the latent multi-criteria rating generation process: the one-stage model LatentMC-1S that utilizes document hashing method to directly compute latent ratings and the two-stage model LatentMC-2S that uses GRU and Gumbel-Softmax for indirect rating generation. Extensive experiments show that the proposed latent multi-criteria rating approaches outperform explicit ratings across different datasets and performance measures. We also show that latent multi-criteria ratings could be used for imputing missing explicit multi-criteria ratings and thus further improving multi-criteria recommender systems.
- 13 October 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 34 (8) , 3854-3866
Learning Latent Multi-Criteria Ratings From User Reviews for Recommendations
Multi-criteria recommender systems have been increasingly useful for helping consumers identify the most relevant items based on different dimensions of user experiences and highlighting their most valued features. Therefore, researchers have proposed various multi-criteria models to improve recommendation performance. However, most of the existing methods utilize only multi-criteria ratings explicitly provided by the users. Note that explicit multi-criteria ratings are sparse and have the problem of missing values. User reviews, on the other hand, contain richer information of user experiences and reveal multi-dimensional user preferences. Therefore, we propose to use latent multi-criteria ratings generated from user reviews, as opposed to explicit multi-criteria ratings, to provide recommendations and capture latent complex heterogeneous user preferences. Specifically, we propose two novel models for the latent multi-criteria rating generation process: the one-stage model LatentMC-1S that utilizes document hashing method to directly compute latent ratings and the two-stage model LatentMC-2S that uses GRU and Gumbel-Softmax for indirect rating generation. Extensive experiments show that the proposed latent multi-criteria rating approaches outperform explicit ratings across different datasets and performance measures. We also show that latent multi-criteria ratings could be used for imputing missing explicit multi-criteria ratings and thus further improving multi-criteria recommender systems.
- Open Access
- 15 September 2020
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
- Vol. 11 (6) , 1-25
Latent Unexpected Recommendations
Unexpected recommender system constitutes an important tool to tackle the problem of filter bubbles and user boredom, which aims at providing unexpected and satisfying recommendations to target users at the same time. Previous unexpected recommendation methods only focus on the straightforward relations between current recommendations and user expectations by modeling unexpectedness in the feature space, thus resulting in the loss of accuracy measures to improve unexpectedness performance. In contrast to these prior models, we propose to model unexpectedness in the latent space of user and item embeddings, which allows us to capture hidden and complex relations between new recommendations and historic purchases. In addition, we develop a novel Latent Closure (LC) method to construct a hybrid utility function and provide unexpected recommendations based on the proposed model. Extensive experiments on three real-world datasets illustrate superiority of our proposed approach over the state-of-the-art unexpected recommendation models, which leads to significant increase in unexpectedness measure without sacrificing any accuracy metric under all experimental settings in this article.
- 15 September 2020
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
- Vol. 11 (6) , 1-25
Open AccessLatent Unexpected Recommendations
Unexpected recommender system constitutes an important tool to tackle the problem of filter bubbles and user boredom, which aims at providing unexpected and satisfying recommendations to target users at the same time. Previous unexpected recommendation methods only focus on the straightforward relations between current recommendations and user expectations by modeling unexpectedness in the feature space, thus resulting in the loss of accuracy measures to improve unexpectedness performance. In contrast to these prior models, we propose to model unexpectedness in the latent space of user and item embeddings, which allows us to capture hidden and complex relations between new recommendations and historic purchases. In addition, we develop a novel Latent Closure (LC) method to construct a hybrid utility function and provide unexpected recommendations based on the proposed model. Extensive experiments on three real-world datasets illustrate superiority of our proposed approach over the state-of-the-art unexpected recommendation models, which leads to significant increase in unexpectedness measure without sacrificing any accuracy metric under all experimental settings in this article.