Wei Yang
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
Wei Yang has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
- Rui Zhong
Xiaohongshu, Beijing, China
5 shared publications - Chi Lu
Kuaishou Technology, Beijing, China
4 shared publications - Peng Jiang
Kuaishou Technology, Beijing, China
4 shared publications - Kun Gai
Kuaishou Technology, Beijing, China
3 shared publications - Chi Lu
Kuaishou Technology, Beijing, China
2 shared publications - Hao Gu
Institute of Automation, Chinese Academy of Sciences, Beijing, China
2 shared publications
Latest Publications
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 2230-2241
TimeMM: Time-as-Operator Spectral Filtering for Dynamic Multimodal Recommendation
Multimodal recommendation improves user modeling by integrating collaborative signals with heterogeneous item content. In real applications, user interests evolve over time and exhibit nonstationary dynamics, where different preference factors change at different rates. This challenge is amplified in multimodal settings because visual and textual cues can dominate decisions under different temporal regimes. Despite strong progress, most multimodal recommenders still rely on static interaction graphs or coarse temporal heuristics, which limits their ability to model continuous preference evolution with fine-grained temporal adaptation. To address these limitations, we propose TimeMM, a time-conditioned spectral filtering framework for dynamic multimodal recommendation. TimeMM instantiates Time-as-Operator by mapping interaction recency to a family of parametric temporal kernels that reweight edges on the user--item graph, producing component-specific representations without explicit eigendecomposition. To capture non-stationary interests, we introduce Adaptive Spectral Filtering that mixes the operator bank according to temporal context, yielding prediction-specific effective spectral responses. To account for modality-specific temporal sensitivity, we further propose Spectral-Aware Modality Routing that calibrates visual and textual contributions conditioned on the same temporal context. Finally, a ranking-space Spectral Diversity Regularization encourages complementary expert behaviors and prevents filter-bank collapse. Extensive experiments on real-world benchmarks demonstrate that TimeMM consistently outperforms state-of-the-art multimodal recommenders while maintaining linear-time scalability.
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 2230-2241
Open AccessTimeMM: Time-as-Operator Spectral Filtering for Dynamic Multimodal Recommendation
Multimodal recommendation improves user modeling by integrating collaborative signals with heterogeneous item content. In real applications, user interests evolve over time and exhibit nonstationary dynamics, where different preference factors change at different rates. This challenge is amplified in multimodal settings because visual and textual cues can dominate decisions under different temporal regimes. Despite strong progress, most multimodal recommenders still rely on static interaction graphs or coarse temporal heuristics, which limits their ability to model continuous preference evolution with fine-grained temporal adaptation. To address these limitations, we propose TimeMM, a time-conditioned spectral filtering framework for dynamic multimodal recommendation. TimeMM instantiates Time-as-Operator by mapping interaction recency to a family of parametric temporal kernels that reweight edges on the user--item graph, producing component-specific representations without explicit eigendecomposition. To capture non-stationary interests, we introduce Adaptive Spectral Filtering that mixes the operator bank according to temporal context, yielding prediction-specific effective spectral responses. To account for modality-specific temporal sensitivity, we further propose Spectral-Aware Modality Routing that calibrates visual and textual contributions conditioned on the same temporal context. Finally, a ranking-space Spectral Diversity Regularization encourages complementary expert behaviors and prevents filter-bank collapse. Extensive experiments on real-world benchmarks demonstrate that TimeMM consistently outperforms state-of-the-art multimodal recommenders while maintaining linear-time scalability.
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 6193-6202
FITMM: Adaptive Frequency-Aware Multimodal Recommendation via Information-Theoretic Representation Learning
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 6193-6202
Open AccessFITMM: Adaptive Frequency-Aware Multimodal Recommendation via Information-Theoretic Representation Learning
- Open Access
- 22 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 411-421
R 4 ec: A Reasoning, Reflection, and Refinement Framework for Recommendation Systems
- 22 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 411-421
Open AccessR 4 ec: A Reasoning, Reflection, and Refinement Framework for Recommendation Systems
- Open Access
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1758-1767
Hierarchical Tree Search-based User Lifelong Behavior Modeling on Large Language Model
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1758-1767
Open AccessHierarchical Tree Search-based User Lifelong Behavior Modeling on Large Language Model
- Open Access
- 8 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 641-650
Hierarchical Sequence ID Representation of Large Language Models for Large-scale Recommendation Systems
- 8 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 641-650
Open AccessHierarchical Sequence ID Representation of Large Language Models for Large-scale Recommendation Systems
- Top Cited PapersOpen Access
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1638-1652
TourRank: Utilizing Large Language Models for Documents Ranking with a Tournament-Inspired Strategy
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1638-1652
Top Cited PapersOpen AccessTourRank: Utilizing Large Language Models for Documents Ranking with a Tournament-Inspired Strategy
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 5663-5672
Multimodal-aware Multi-intention Learning for Recommendation
Whether it is an e-commerce platform or a short video platform, the effective use of multi-modal data plays an important role in the recommendation system. More and more researchers are exploring how to effectively use multimodal signals to entice more users to buy goods or watch short videos. Some studies have added multimodal features as side information to the model and achieved certain results. In practice, the purchase behavior of users mainly depends on some personalized intentions. However, it is difficult for neural networks to process noise information and extract high-level intention information effectively. To investigate the benefits of latent intentions and leverage them effectively for recommendation, we propose a Multimodal-aware Multi-intention Learning method for recommendation (MMIL). Specifically, we first construct a multi-intention recommendation framework based on the probability distribution relationship among predicted objectives and intentions, while avoiding intention overfitting. We then design an intention representation learning module to learn accurate multiple intention representations based on intention prototypes. Further, we propose a multi-modal intention perceptron module to learn multi-modal intention representations. In addition, we design self-supervised intention-based and representation-based contrastive objectives to achieve cross-modal representation alignment. On three real-world data sets, the proposed MMIL method outperforms other advanced techniques. The effectiveness of intention modeling and intention alignment is verified by comprehensive experiments. The source code is available at: https://github.com/ml-mindset/MMIL.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 5663-5672
Open AccessMultimodal-aware Multi-intention Learning for Recommendation
Whether it is an e-commerce platform or a short video platform, the effective use of multi-modal data plays an important role in the recommendation system. More and more researchers are exploring how to effectively use multimodal signals to entice more users to buy goods or watch short videos. Some studies have added multimodal features as side information to the model and achieved certain results. In practice, the purchase behavior of users mainly depends on some personalized intentions. However, it is difficult for neural networks to process noise information and extract high-level intention information effectively. To investigate the benefits of latent intentions and leverage them effectively for recommendation, we propose a Multimodal-aware Multi-intention Learning method for recommendation (MMIL). Specifically, we first construct a multi-intention recommendation framework based on the probability distribution relationship among predicted objectives and intentions, while avoiding intention overfitting. We then design an intention representation learning module to learn accurate multiple intention representations based on intention prototypes. Further, we propose a multi-modal intention perceptron module to learn multi-modal intention representations. In addition, we design self-supervised intention-based and representation-based contrastive objectives to achieve cross-modal representation alignment. On three real-world data sets, the proposed MMIL method outperforms other advanced techniques. The effectiveness of intention modeling and intention alignment is verified by comprehensive experiments. The source code is available at: https://github.com/ml-mindset/MMIL.
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 10611-10620
Enhancing Transformer-based Semantic Matching for Few-shot Learning through Weakly Contrastive Pre-training
The task of text semantic matching focuses on measuring the semantic similarity between two texts and is widely applied in search and ranking scenarios. In recent years, pre-trained foundation models based on the Transformer architecture have demonstrated powerful semantic representation capabilities. The pipeline of fine-tuning pre-trained foundation models on downstream semantic matching tasks has achieved promising results and widespread adoption. However, practical downstream scenarios often face severe challenges in terms of data quality and quantity. Ensuring high-quality and large quantities of samples is often difficult. Current research on enhancing pre-trained models for few-shot text semantic matching tasks is still not advanced enough. Therefore, this paper focuses on providing a general enhancement scheme for few-shot text semantic matching tasks. Specifically, we propose an Enhancing Transformer-based Semantic Matching method for few-shot learning through weakly contrastive pre-training, which is named as SEMFormer. First, starting from the token-level and structural-level perspectives, we design a simple and low-cost data augmentation method to construct weakly supervised samples. Then, we use the global semantic representations to construct a contrastive objective from the relation-aspect perspective. Next, we design a contrastive objective based on the alignment-aspect, aiming to achieve effective semantic matching by optimizing the bidirectional semantic awareness between texts. We conducted comprehensive experiments based on five Chinese and English datasets. The experimental results validated that our proposed weakly contrastive pre-training augmentation method significantly improves model performance. Further experiments confirmed the effectiveness of our design. The source code is available at: https://github.com/llm-ml/SEMFormer.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 10611-10620
Open AccessEnhancing Transformer-based Semantic Matching for Few-shot Learning through Weakly Contrastive Pre-training
The task of text semantic matching focuses on measuring the semantic similarity between two texts and is widely applied in search and ranking scenarios. In recent years, pre-trained foundation models based on the Transformer architecture have demonstrated powerful semantic representation capabilities. The pipeline of fine-tuning pre-trained foundation models on downstream semantic matching tasks has achieved promising results and widespread adoption. However, practical downstream scenarios often face severe challenges in terms of data quality and quantity. Ensuring high-quality and large quantities of samples is often difficult. Current research on enhancing pre-trained models for few-shot text semantic matching tasks is still not advanced enough. Therefore, this paper focuses on providing a general enhancement scheme for few-shot text semantic matching tasks. Specifically, we propose an Enhancing Transformer-based Semantic Matching method for few-shot learning through weakly contrastive pre-training, which is named as SEMFormer. First, starting from the token-level and structural-level perspectives, we design a simple and low-cost data augmentation method to construct weakly supervised samples. Then, we use the global semantic representations to construct a contrastive objective from the relation-aspect perspective. Next, we design a contrastive objective based on the alignment-aspect, aiming to achieve effective semantic matching by optimizing the bidirectional semantic awareness between texts. We conducted comprehensive experiments based on five Chinese and English datasets. The experimental results validated that our proposed weakly contrastive pre-training augmentation method significantly improves model performance. Further experiments confirmed the effectiveness of our design. The source code is available at: https://github.com/llm-ml/SEMFormer.
- Open Access
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 6369-6378
Modal-aware Bias Constrained Contrastive Learning for Multimodal Recommendation
Multimodal recommendation system has been widely used in short video platform, e-commerce platform and news media. Multimodal data contains information such as product image and product text, which is often used as auxiliary signal to improve the effect of recommendation system significantly. In order to alleviate the problems of data sparsity and noise, some researchers construct data augmentation to use self-supervised learning to help model training. These methods have achieved certain results. However, most of the work is based on data augmentation in random ways, such as random masking and random perturbation. This random method is likely to lose important information and introduce new noise, resulting in biased augmentation data. Therefore, we propose a Modal-aware Bias Constrained Contrastive Learning method (BCCL) to solve the above problems. Specifically, BCCL introduces a bias-constrained data augmentation method to ensure the quality of augmentation samples. Then the multi-modal semantic information is modeled by the designed modal awareness module. Furthermore, we propose a information alignment module to improve the sparse modal feature learning of the model. We conducted a comprehensive experiment on three real-world data sets, and the experimental results showed that the proposed BCCL outperformed all the state-of-art methods. In-depth experiments have verified the effectiveness of our proposed modules.
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 6369-6378
Open AccessModal-aware Bias Constrained Contrastive Learning for Multimodal Recommendation
Multimodal recommendation system has been widely used in short video platform, e-commerce platform and news media. Multimodal data contains information such as product image and product text, which is often used as auxiliary signal to improve the effect of recommendation system significantly. In order to alleviate the problems of data sparsity and noise, some researchers construct data augmentation to use self-supervised learning to help model training. These methods have achieved certain results. However, most of the work is based on data augmentation in random ways, such as random masking and random perturbation. This random method is likely to lose important information and introduce new noise, resulting in biased augmentation data. Therefore, we propose a Modal-aware Bias Constrained Contrastive Learning method (BCCL) to solve the above problems. Specifically, BCCL introduces a bias-constrained data augmentation method to ensure the quality of augmentation samples. Then the multi-modal semantic information is modeled by the designed modal awareness module. Furthermore, we propose a information alignment module to improve the sparse modal feature learning of the model. We conducted a comprehensive experiment on three real-world data sets, and the experimental results showed that the proposed BCCL outperformed all the state-of-art methods. In-depth experiments have verified the effectiveness of our proposed modules.
- Open Access
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 2959-2968
Multimodal Optimal Transport Knowledge Distillation for Cross-domain Recommendation
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 2959-2968
Open AccessMultimodal Optimal Transport Knowledge Distillation for Cross-domain Recommendation