Shuai Xu
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
Shuai Xu has a total of 80 co-authors. Here are the top co-authors by number of shared publications:
- Yicong Li
Nanjing University of Aeronautics and Astronautics, Nanjing, Jiangsu, China
7 shared publications - Xiaoming Fu
University of Göttingen
6 shared publications - Jiuxin Cao
Southeast University, Nanjing, China and Purple Mountain Laboratories, Nanjing, China
5 shared publications - Bohan Li
Nanjing University of Aeronautics and Astronautics, Nanjing, China
4 shared publications - Donghai Guan
Nanjing University of Aeronautics and Astronautics, Nanjing, China
4 shared publications - Jianqiu Xu
Nanjing University of Aeronautics and Astronautics, Nanjing, China
4 shared publications
Latest Publications
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 7847-7852
Adaptive Preference Allocation and Semantic Hard-Negative Supervision for Multimodal Recommendation
Multimodal recommendation enhances user preference modeling by leveraging visual and textual content. However, existing methods generally adopt a unified modality fusion strategy, making it difficult to capture users' diverse reliance on visual and textual signals. Meanwhile, random negative sampling provides limited ranking supervision and is insufficient for modeling fine-grained preference boundaries. To address these issues, we propose an Adaptive Preference allocation and Semantic Negative supervision framework called APSN, which explicitly models personalized preferences through user-level modality contribution allocation, thereby learning more fine-grained multimodal user representations. To enhance ranking supervision, APSN samples informative semantic negatives from dynamically constructed user communities, guiding the model to better capture users' preference boundaries. In addition, APSN improves feature robustness via masked semantic consistency and complements local structural information through a sparse collaborative view. Experimental results on multiple public datasets demonstrate that APSN can achieve consistent and effective improvements in recommendation performance. Code is available at https://github.com/jcs12123/APSN.
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 7847-7852
Open AccessAdaptive Preference Allocation and Semantic Hard-Negative Supervision for Multimodal Recommendation
Multimodal recommendation enhances user preference modeling by leveraging visual and textual content. However, existing methods generally adopt a unified modality fusion strategy, making it difficult to capture users' diverse reliance on visual and textual signals. Meanwhile, random negative sampling provides limited ranking supervision and is insufficient for modeling fine-grained preference boundaries. To address these issues, we propose an Adaptive Preference allocation and Semantic Negative supervision framework called APSN, which explicitly models personalized preferences through user-level modality contribution allocation, thereby learning more fine-grained multimodal user representations. To enhance ranking supervision, APSN samples informative semantic negatives from dynamically constructed user communities, guiding the model to better capture users' preference boundaries. In addition, APSN improves feature robustness via masked semantic consistency and complements local structural information through a sparse collaborative view. Experimental results on multiple public datasets demonstrate that APSN can achieve consistent and effective improvements in recommendation performance. Code is available at https://github.com/jcs12123/APSN.
- 19 October 2026
- Published by Springer Nature
- p. 128-147
Duration-Aware Ternary Temporal Graph Network for Career Trajectory Prediction
- 19 October 2026
- Published by Springer Nature
- p. 128-147
Duration-Aware Ternary Temporal Graph Network for Career Trajectory Prediction
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (10) , 6658-6671
GEM-Distill: Graph Ensemble Multi-Level Distillation for MLP-Based Graph Classification
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (10) , 6658-6671
GEM-Distill: Graph Ensemble Multi-Level Distillation for MLP-Based Graph Classification
- 26 September 2026
- Published by Springer Nature
- p. 299-313
LADI: Logic-Aware Dual Injection for Instruction-Guided Image Editing via Structural-Semantic Disentanglement
- 26 September 2026
- Published by Springer Nature
- p. 299-313
LADI: Logic-Aware Dual Injection for Instruction-Guided Image Editing via Structural-Semantic Disentanglement
- 23 June 2026
- Published by Springer Nature
- p. 179-192
CTP2KL: Collaborative Trajectory Protection Against Knowing-and-Learning Attacks in Multiple Location-Based Services
- 23 June 2026
- Published by Springer Nature
- p. 179-192
CTP2KL: Collaborative Trajectory Protection Against Knowing-and-Learning Attacks in Multiple Location-Based Services
- Open Access
- 1 June 2026
- Published by Tsinghua University Press in Tsinghua Science and Technology
- Vol. 31 (6) , 2792-2821
A Survey of Zero-Shot Image Classification: Concepts, Developments, and Challenges
Zero-shot learning is gaining increasing attention in the social computing community, primarily because it can enable models to effectively perform classification or regression tasks when new concepts continually emerge while lacking sufficient training samples in certain categories. Zero-shot image classification, as a concrete application of zero-shot learning, requires the model to classify images into unknown categories without seeing any training samples of those categories. The key issue of zero-shot image classification is how to leverage auxiliary information such as attributes and textual descriptions to establish connections between the visual space and the semantic space. With the advancement of deep learning theories and methods, the way of modeling cross-modal interaction has continuously improved, promoting significant progress in zero-shot image classification. In this survey, we intensively review related literature in the field of zero-shot image classification over the past decade, with specific elaborations on the latest progress under three scenarios: Traditional zero-shot learning, generalized zero-shot learning, and compositional zero-shot learning. Besides, challenges that need to be addressed as well as prospects of emerging techniques like large language models in zero-shot image classification are also discussed.
- 1 June 2026
- Published by Tsinghua University Press in Tsinghua Science and Technology
- Vol. 31 (6) , 2792-2821
Open AccessA Survey of Zero-Shot Image Classification: Concepts, Developments, and Challenges
Zero-shot learning is gaining increasing attention in the social computing community, primarily because it can enable models to effectively perform classification or regression tasks when new concepts continually emerge while lacking sufficient training samples in certain categories. Zero-shot image classification, as a concrete application of zero-shot learning, requires the model to classify images into unknown categories without seeing any training samples of those categories. The key issue of zero-shot image classification is how to leverage auxiliary information such as attributes and textual descriptions to establish connections between the visual space and the semantic space. With the advancement of deep learning theories and methods, the way of modeling cross-modal interaction has continuously improved, promoting significant progress in zero-shot image classification. In this survey, we intensively review related literature in the field of zero-shot image classification over the past decade, with specific elaborations on the latest progress under three scenarios: Traditional zero-shot learning, generalized zero-shot learning, and compositional zero-shot learning. Besides, challenges that need to be addressed as well as prospects of emerging techniques like large language models in zero-shot image classification are also discussed.
- 24 February 2026
- Published by Springer Nature
- p. 236-251
DCSN: Dynamic Calibration and Contrastive Sharpening for MultiModal Recommendation
- 24 February 2026
- Published by Springer Nature
- p. 236-251
DCSN: Dynamic Calibration and Contrastive Sharpening for MultiModal Recommendation
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 2105-2114
Usefulness and Diminishing Returns: Evaluating Social Information in Recommender Systems
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 2105-2114
Open AccessUsefulness and Diminishing Returns: Evaluating Social Information in Recommender Systems
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 2042-2051
Multimodal Sentiment Analysis with Multi-Perspective Thinking via Large Multimodal Models
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 2042-2051
Open AccessMultimodal Sentiment Analysis with Multi-Perspective Thinking via Large Multimodal Models
- 10 October 2025
- Published by Springer Nature in World Wide Web
- Vol. 28 (6) , 1-24
TiDGRec: dual-graph modeling with target-intention filtering for session-based recommendation
- 10 October 2025
- Published by Springer Nature in World Wide Web
- Vol. 28 (6) , 1-24
TiDGRec: dual-graph modeling with target-intention filtering for session-based recommendation