Li Yu
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
Li Yu has a total of 35 co-authors. Here are the top co-authors by number of shared publications:
- Qihan Du
School of Information, Renmin University of China, Beijing, China
4 shared publications - Youfang Leng
Renmin University of China, China
4 shared publications - Dongsong Zhang
Belk College of Business & The School of Data Science, The University of North Carolina at Charlotte, Charlotte, North Carolina 28223
3 shared publications - Huiyuan Li
Renmin University of China, China
3 shared publications - Xi Niu
University of North Carolina at Charlotte
3 shared publications - Jie Xiong
Southwestern University of Finance and Economics, Chengdu, China
2 shared publications
Latest Publications
- 1 January 2026
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in INFORMS Journal on Computing
- Vol. 38 (1) , 1-15
From Interaction to Prediction: A Multi-Interactive Attention-Based Approach to Product Rating Prediction
Despite increasing research on product rating prediction, very few studies have considered user-item interaction relationships at multiple levels. To address this critical limitation, we propose a novel rating prediction method based on multi-interaction attention (RPMIA) by learning user-item interaction relationships at three levels simultaneously from online consumer reviews for predicting product ratings with reasonable interpretability. Specifically, RPMIA first deploys a multihead cross-attention mechanism to capture the interaction between contexts of items and users. Then, it uses a bilayer gate-based mechanism to extract the aspects of items and users and a self-attention mechanism to learn their interaction at the aspect level. Finally, the aspects of users and items are coupled together to form meaningful user-item aspect pairs via a joint attention. A multitask predictor that integrates a factorization machine and a feedforward neural network is designed to generate a rating prediction. We empirically evaluated RPMIA with seven real-world data sets. The results demonstrate that RPMIA outperforms the state-of-the-art methods consistently and significantly. We also conduct a user study to assess the interpretability of the RPMIA method. History: Accepted by Ram Ramesh, Area Editor for Data Science & Machine Learning. Funding: The research is supported by Beijing Social Science Foundation [24XCB012], Suzhou Key Laboratory of Artificial Intelligence and Social Governance Technologies [SZS2023007], and Smart Social Governance Technology and Innovative Application Platform [YZCXPT2023101]. Supplemental Material: The software that supports the findings of this study is available within the paper and its Supplemental Information ( https://pubsonline.informs.org/doi/suppl/10.1287/ijoc.2023.0131 ) as well as from the IJOC GitHub software repository ( https://github.com/INFORMSJoC/2023.0131 ). The complete IJOC Software and Data Repository is available at https://informsjoc.github.io/ .
- 1 January 2026
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in INFORMS Journal on Computing
- Vol. 38 (1) , 1-15
From Interaction to Prediction: A Multi-Interactive Attention-Based Approach to Product Rating Prediction
Despite increasing research on product rating prediction, very few studies have considered user-item interaction relationships at multiple levels. To address this critical limitation, we propose a novel rating prediction method based on multi-interaction attention (RPMIA) by learning user-item interaction relationships at three levels simultaneously from online consumer reviews for predicting product ratings with reasonable interpretability. Specifically, RPMIA first deploys a multihead cross-attention mechanism to capture the interaction between contexts of items and users. Then, it uses a bilayer gate-based mechanism to extract the aspects of items and users and a self-attention mechanism to learn their interaction at the aspect level. Finally, the aspects of users and items are coupled together to form meaningful user-item aspect pairs via a joint attention. A multitask predictor that integrates a factorization machine and a feedforward neural network is designed to generate a rating prediction. We empirically evaluated RPMIA with seven real-world data sets. The results demonstrate that RPMIA outperforms the state-of-the-art methods consistently and significantly. We also conduct a user study to assess the interpretability of the RPMIA method. History: Accepted by Ram Ramesh, Area Editor for Data Science & Machine Learning. Funding: The research is supported by Beijing Social Science Foundation [24XCB012], Suzhou Key Laboratory of Artificial Intelligence and Social Governance Technologies [SZS2023007], and Smart Social Governance Technology and Innovative Application Platform [YZCXPT2023101]. Supplemental Material: The software that supports the findings of this study is available within the paper and its Supplemental Information ( https://pubsonline.informs.org/doi/suppl/10.1287/ijoc.2023.0131 ) as well as from the IJOC GitHub software repository ( https://github.com/INFORMSJoC/2023.0131 ). The complete IJOC Software and Data Repository is available at https://informsjoc.github.io/ .
- 1 May 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 284
BiG: A bidirectional group-wise contrastive learning method for multi-label text classification
- 1 May 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 284
BiG: A bidirectional group-wise contrastive learning method for multi-label text classification
- Open Access
- 26 February 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 43 (3) , 1-27
MVideoRec: Micro Video Recommendations through Modality Decomposition and Contrastive Learning
Personalized micro video recommendation aims to recommend the micro videos tailored to user preference based on the user’s interaction history with the micro videos, which has drawn increasing attention from both the academic and industrial communities. Existing solutions primarily concentrate on video-level interactions between users and micro videos to model their preferences, and cannot distinguish the finer-grained users’ interactions with various modalities. Ignoring modality-level interactions prevents the full understanding of the user’s true and subtle preferences on micro videos. To this end, in this article, we propose a Contrastive Multimodal Interaction Graph Learning ( MVideoRec ) model to automatically and explicitly learn the modality-level interaction between users and micro videos for recommendations. Specifically, we designed a graph structure learning module with a sparsification strategy to infer modality-level interaction graph, which will be dynamically and iteratively updated based on the node representations obtained from the node representation learning module. Furthermore, to address the lack of ground truth labels, we propose to generate teacher view from video-level interaction graph and student view from modality-level interaction graph, as well as construct intra-modality and inter-modality contrastive pairwise instances to provide self-supervised signals. Extensive experiments on three real-world micro video datasets validate the effectiveness of MVideoRec.
- 26 February 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 43 (3) , 1-27
Open AccessMVideoRec: Micro Video Recommendations through Modality Decomposition and Contrastive Learning
Personalized micro video recommendation aims to recommend the micro videos tailored to user preference based on the user’s interaction history with the micro videos, which has drawn increasing attention from both the academic and industrial communities. Existing solutions primarily concentrate on video-level interactions between users and micro videos to model their preferences, and cannot distinguish the finer-grained users’ interactions with various modalities. Ignoring modality-level interactions prevents the full understanding of the user’s true and subtle preferences on micro videos. To this end, in this article, we propose a Contrastive Multimodal Interaction Graph Learning ( MVideoRec ) model to automatically and explicitly learn the modality-level interaction between users and micro videos for recommendations. Specifically, we designed a graph structure learning module with a sparsification strategy to infer modality-level interaction graph, which will be dynamically and iteratively updated based on the node representations obtained from the node representation learning module. Furthermore, to address the lack of ground truth labels, we propose to generate teacher view from video-level interaction graph and student view from modality-level interaction graph, as well as construct intra-modality and inter-modality contrastive pairwise instances to provide self-supervised signals. Extensive experiments on three real-world micro video datasets validate the effectiveness of MVideoRec.
- 17 January 2025
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in INFORMS Journal on Computing
Code and Data Repository for From Interaction to Prediction: A Multi-Interactive Attention based Approach to Product Rating Prediction
The software and data in this repository are a snapshot of the software and data that were used in the research reported on in the paper From Interaction to Prediction: A Multi-Interactive Attention based Approach to Product Rating Prediction by Yu L, Gong W, Zhang D, Ding Y and Fu Z.
- 17 January 2025
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in INFORMS Journal on Computing
Code and Data Repository for From Interaction to Prediction: A Multi-Interactive Attention based Approach to Product Rating Prediction
The software and data in this repository are a snapshot of the software and data that were used in the research reported on in the paper From Interaction to Prediction: A Multi-Interactive Attention based Approach to Product Rating Prediction by Yu L, Gong W, Zhang D, Ding Y and Fu Z.
- Open Access
- 10 August 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 18 (1) , 1-28
Sequential and Graphical Cross-Domain Recommendations with a Multi-View Hierarchical Transfer Gate
Cross-domain recommender systems could potentially improve the recommendation performance by means of transferring abundant knowledge from the auxiliary domain to the target domain. They could help address some key challenges in recommender systems, such as data sparsity and cold start. However, most existing cross-domain recommendation approaches represent the user preferences based on a single kind of user’s feature or behavior and fail to explore the hidden interaction effects of different kinds of features or behaviors. In this article, we propose the S equential and G raphical Cross -Domain Recommendations with a Multi-View Hierarchical Transfer Gate (SGCross) to transfer user representations from multiple perspectives. The SGCross model constructs a user profile by learning the personal preference from a personal view, the dynamic preference from a temporal view, as well as the collaborative preference from a collaborative view. Specifically, a Multi-view Hierarchical Gate (MHG) is designed to transfer the informative representations of user knowledge on different views from the auxiliary domain separately, aiming to enhance the user representations. Furthermore, a two-stage attentive fusion module is designed to integrate transferred information at two levels: the domain level and the view level. Extensive experiments on the Amazon dataset and the Douban dataset have demonstrated that SGCross effectively improves the accuracy of cross-domain recommendations and outperforms the state-of-the-art baseline models.
- 10 August 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 18 (1) , 1-28
Open AccessSequential and Graphical Cross-Domain Recommendations with a Multi-View Hierarchical Transfer Gate
Cross-domain recommender systems could potentially improve the recommendation performance by means of transferring abundant knowledge from the auxiliary domain to the target domain. They could help address some key challenges in recommender systems, such as data sparsity and cold start. However, most existing cross-domain recommendation approaches represent the user preferences based on a single kind of user’s feature or behavior and fail to explore the hidden interaction effects of different kinds of features or behaviors. In this article, we propose the S equential and G raphical Cross -Domain Recommendations with a Multi-View Hierarchical Transfer Gate (SGCross) to transfer user representations from multiple perspectives. The SGCross model constructs a user profile by learning the personal preference from a personal view, the dynamic preference from a temporal view, as well as the collaborative preference from a collaborative view. Specifically, a Multi-view Hierarchical Gate (MHG) is designed to transfer the informative representations of user knowledge on different views from the auxiliary domain separately, aiming to enhance the user representations. Furthermore, a two-stage attentive fusion module is designed to integrate transferred information at two levels: the domain level and the view level. Extensive experiments on the Amazon dataset and the Douban dataset have demonstrated that SGCross effectively improves the accuracy of cross-domain recommendations and outperforms the state-of-the-art baseline models.
- Open Access
- 18 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 739-748
Wisdom of Crowds and Fine-Grained Learning for Serendipity Recommendations
- 18 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 739-748
Open AccessWisdom of Crowds and Fine-Grained Learning for Serendipity Recommendations
- 18 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
M3Rec: Cross-Modal Context Enhanced Micro-Video Recommendation with Mutual Information Maximization
Personalized recommendation of micro-videos is crucial for many content sharing platforms. Micro-videos typically com-prise fruitful multimodal contents. Existing methods have limitations in learning multimodal representations: (i) They suffer from data sparsity problems as only rely on the inter-action prediction loss to train the whole model. (ii) They do not consider the correlation among multimodal contents into the representation learning. To tackle these limitations, we propose a cross-Modal context enhanced method via Mutual infoMax for Recommendation, termed M 3 Rec. Specifically, we design the cross-modal graph neural network to inter-change multimodal information to generate modality-aware representations. Then, based on the coupled modality con-text, we design the masked modality prediction (MMP) with three self-supervised objectives to learn the correlation among visual, textual, and acoustic contents empowered by the mu-tual information maximization principle. Finally, we enhance representations via self-supervised pre-training to boost rec-ommendation. Extensive experiments demonstrate that our approach outperforms existing state-of-the-art methods.
- 18 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
M3Rec: Cross-Modal Context Enhanced Micro-Video Recommendation with Mutual Information Maximization
Personalized recommendation of micro-videos is crucial for many content sharing platforms. Micro-videos typically com-prise fruitful multimodal contents. Existing methods have limitations in learning multimodal representations: (i) They suffer from data sparsity problems as only rely on the inter-action prediction loss to train the whole model. (ii) They do not consider the correlation among multimodal contents into the representation learning. To tackle these limitations, we propose a cross-Modal context enhanced method via Mutual infoMax for Recommendation, termed M 3 Rec. Specifically, we design the cross-modal graph neural network to inter-change multimodal information to generate modality-aware representations. Then, based on the coupled modality con-text, we design the masked modality prediction (MMP) with three self-supervised objectives to learn the correlation among visual, textual, and acoustic contents empowered by the mu-tual information maximization principle. Finally, we enhance representations via self-supervised pre-training to boost rec-ommendation. Extensive experiments demonstrate that our approach outperforms existing state-of-the-art methods.
- Open Access
Show Me the Whole World: Towards Entire Item Space Exploration for Interactive Personalized Recommendations
User interest exploration is an important and challenging topic in recommender systems, which alleviates the closed-loop effects between recommendation models and user-item interactions. Contextual bandit (CB) algorithms strive to make a good trade-off between exploration and exploitation so that users' potential interests have chances to expose. However, classical CB algorithms can only be applied to a small, sampled item set (usually hundreds), which forces the typical applications in recommender systems limited to candidate post-ranking, homepage top item ranking, ad creative selection, or online model selection (A/B test). In this paper, we introduce two simple but effective hierarchical CB algorithms to make a classical CB model (such as LinUCB and Thompson Sampling) capable to explore users' interest in the entire item space without limiting it to a small item set. We first construct a hierarchy item tree via a bottom-up clustering algorithm to organize items in a coarse-to-fine manner. Then we propose a hierarchical CB (HCB) algorithm to explore users' interest in the hierarchy tree. HCB takes the exploration problem as a series of decision-making processes, where the goal is to find a path from the root to a leaf node, and the feedback will be back-propagated to all the nodes in the path. We further propose a progressive hierarchical CB (pHCB) algorithm, which progressively extends visible nodes which reach a confidence level for exploration, to avoid misleading actions on upper-level nodes in the sequential decision-making process. Extensive experiments on two public recommendation datasets demonstrate the effectiveness and flexibility of our methods.
Open AccessShow Me the Whole World: Towards Entire Item Space Exploration for Interactive Personalized Recommendations
User interest exploration is an important and challenging topic in recommender systems, which alleviates the closed-loop effects between recommendation models and user-item interactions. Contextual bandit (CB) algorithms strive to make a good trade-off between exploration and exploitation so that users' potential interests have chances to expose. However, classical CB algorithms can only be applied to a small, sampled item set (usually hundreds), which forces the typical applications in recommender systems limited to candidate post-ranking, homepage top item ranking, ad creative selection, or online model selection (A/B test). In this paper, we introduce two simple but effective hierarchical CB algorithms to make a classical CB model (such as LinUCB and Thompson Sampling) capable to explore users' interest in the entire item space without limiting it to a small item set. We first construct a hierarchy item tree via a bottom-up clustering algorithm to organize items in a coarse-to-fine manner. Then we propose a hierarchical CB (HCB) algorithm to explore users' interest in the hierarchy tree. HCB takes the exploration problem as a series of decision-making processes, where the goal is to find a path from the root to a leaf node, and the feedback will be back-propagated to all the nodes in the path. We further propose a progressive hierarchical CB (pHCB) algorithm, which progressively extends visible nodes which reach a confidence level for exploration, to avoid misleading actions on upper-level nodes in the sequential decision-making process. Extensive experiments on two public recommendation datasets demonstrate the effectiveness and flexibility of our methods.
- 6 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3610-3614
Co-Capsule Networks Based Knowledge Transfer for Cross-Domain Recommendation
Cross-domain recommendation (CDR) technology is proved to be an effective way to tackle the difficulties encountered by traditional recommender technology (e.g. CF), such as data sparsity and cold-start. However, on account of the heterogeneity, it is difficult to enhance the representation of user preferences with the informative knowledge of shared user learned from auxiliary domain. In this paper, we propose a CDR method with co-capsule networks based knowledge transfer to implement the recommendation for the cold-start users. Concretely, the model captures the preference of users with a two-tier structure, the attentive GRU is employed to learn the primary intent from item level and the capsule network is used to further refer the user interests in feature level. After studying the mapping matrix, NeuMF is adapted to execute the recommendation task. We conduct extensive experiments on public datasets and the results demonstrate that the proposed model outperforms many state-of-the-art models.
- 6 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3610-3614
Co-Capsule Networks Based Knowledge Transfer for Cross-Domain Recommendation
Cross-domain recommendation (CDR) technology is proved to be an effective way to tackle the difficulties encountered by traditional recommender technology (e.g. CF), such as data sparsity and cold-start. However, on account of the heterogeneity, it is difficult to enhance the representation of user preferences with the informative knowledge of shared user learned from auxiliary domain. In this paper, we propose a CDR method with co-capsule networks based knowledge transfer to implement the recommendation for the cold-start users. Concretely, the model captures the preference of users with a two-tier structure, the attentive GRU is employed to learn the primary intent from item level and the capsule network is used to further refer the user interests in feature level. After studying the mapping matrix, NeuMF is adapted to execute the recommendation task. We conduct extensive experiments on public datasets and the results demonstrate that the proposed model outperforms many state-of-the-art models.
- Open Access
- 30 March 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 51618-51630
Hierarchical Context-Aware Recurrent Network for Session-Based Recommendation
Recently, session-based recommendations are becoming popular to explore the temporal characteristics of customers’ interactive behaviors. The user’s behavior in the session not only contains the item sequence but also rich context information such as how the user navigates to the item, the operation type, and the dwell time on the item, which may impact users’ next actions. How to incorporate these contextual features effectively for session-based recommendations remains a great challenge. In this paper, we divide them into two hierarchies: session-context at the macro-level and event-context at the micro-level, and then propose a Hierarchical Context-aware Recurrent Network (HiCAR) by incorporating both users’ micro-interaction with the item and the two-hierarchy contexts, wherein a Session Context Learning module with the n-way hybrid strategy is adopted to model multi-feature interactions in the session-context. Moreover, an Event Context Learning module consists of TIME-LSTM with a time gate is designed to model the sequential behavior with event-context. By experimenting on two real-world datasets, we find that our HiCAR model outperforms state-of-the-art baselines on both datasets, which demonstrates its advantages in modeling users’ sequential behaviors and contexts simultaneously.
- 30 March 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 51618-51630
Open AccessHierarchical Context-Aware Recurrent Network for Session-Based Recommendation
Recently, session-based recommendations are becoming popular to explore the temporal characteristics of customers’ interactive behaviors. The user’s behavior in the session not only contains the item sequence but also rich context information such as how the user navigates to the item, the operation type, and the dwell time on the item, which may impact users’ next actions. How to incorporate these contextual features effectively for session-based recommendations remains a great challenge. In this paper, we divide them into two hierarchies: session-context at the macro-level and event-context at the micro-level, and then propose a Hierarchical Context-aware Recurrent Network (HiCAR) by incorporating both users’ micro-interaction with the item and the two-hierarchy contexts, wherein a Session Context Learning module with the n-way hybrid strategy is adopted to model multi-feature interactions in the session-context. Moreover, an Event Context Learning module consists of TIME-LSTM with a time gate is designed to model the sequential behavior with event-context. By experimenting on two real-world datasets, we find that our HiCAR model outperforms state-of-the-art baselines on both datasets, which demonstrates its advantages in modeling users’ sequential behaviors and contexts simultaneously.