NSTL国家科技图书文献中心

1. Graph Contrastive Learning for Multi-behavior Recommendation NSTL国家科技图书文献中心

Haiying Li | Huihui Wang ... - 《Advanced Data Mining and Applications,Part VI》 - International Conference on Advanced Data Mining and Applications - 2025, - 34～48 - 共15页

摘要： for recommendation. Multi-behavior recommendation | Learning for Multi-Behavior* Recommendation (GCLMBR* | improve recommendation performance. Most existing multi | -behavior* recommendation methods are usually insufficient* | multi-behavior data, and integrate the learned single

关键词： Multi-Behavior recommendation | Graph contrastive learning | Graph convolutional network

2. Contrastive Clustering Learning for Multi-Behavior Recommendation NSTL国家科技图书文献中心

WEI LAN | GUOXIAN ZHOU ... - 《ACM transactions on information systems》 - 2025,43(1) - 18.1～18.23 - 共23页

摘要：Increasing multiple behavior recommendation | behavior. This article proposes a novel multi-behavior | recommendation model based on contrastive clustering learning | (including behavior-level embedding, instance-level | optimize the embeddings of users and items. In behavior

关键词： Multi-behavior Recommendation | Data Sparsity | Contrastive Learning | Contrastive Clustering Learning

3. Multi-Behavior Recommendation with Personalized Directed Acyclic Behavior Graphs NSTL国家科技图书文献中心

XI ZHU | FAKE LIN ... - 《ACM transactions on information systems》 - 2025,43(1) - 20.1～20.30 - 共30页

摘要：. However, many existing solutions for multi-behavior | items involved in the multi-behavior* interactions. To* | Convolutional Network (DA-GCN) for the multi-behavior | A well-developed recommendation* system can not* | only leverage multi-typed interactions (such as page

关键词： Multi-Behavior Recommendation | Directed Acyclic Graph | Graph Neural Network

4. MHHCR: Multi-behavior Heterogeneous Hypergraph Contrastive Recommendation NSTL国家科技图书文献中心

Yiheng Li | Weihai Lu - 《Web Information Systems Engineering - WISE 2024,Part III》 - International Conference on Web Information Systems Engineering - 2025, - 91～102 - 共12页

摘要：Multi-behavior graph recommendation systems | novel recommendation framework Multi-behavior | behavior patterns and preferences and handling | Heterogeneous Hypergraph Contrastive Recommendation* (MHHCR* | can simultaneously consider various user behaviors

关键词： Multi-behavior recommendation | Contrastive learning | Graph neural networks

5. Learning multi-behavior user intent for session-based recommendation NSTL国家科技图书文献中心

Yu Zhang | Xiaoyan Zhu ... - 《Expert Systems with Application》 - 2025,259(Jan.) - 125269.1～125269.11 - 共11页

摘要：-behavior* User Intent Recommendation model (MUIR) to* | Session-based recommendation* makes a* | recommendation by exploiting short-term user interaction and | recommendation. Although effective, these methods focus on a | particular behavior* or fail to model the complex*

关键词： Recommendation | Session-based recommendation | Multi-behavior modeling

6. Research on Micro-videos Recommendation Method Integrating Multimodal Data and User Multi-behavior NSTL国家科技图书文献中心

Wangwang Zhang | Baojun Tian ... - 《Web Information Systems Engineering - WISE 2024,Part III》 - International Conference on Web Information Systems Engineering - 2025, - 3～16 - 共14页

摘要： (Multi-Modal User Behavior* Graph Neural Network, MMUB* | Existing micro-video recommendation* methods* | multimodal information to enhance the recommendation* effect* | same time, the existing micro-video recommendation | leads to the limitation of the recommendation* results*

关键词： Multi-behavior | Multimodal data | Heterogeneous graph neural networks | Recommendation systems

7. The Research of Sequence Recommendation Method Based on Heterogeneous Enhanced Transformer with Multi-behavior Data NSTL国家科技图书文献中心

Tengjiao Wang | Baojun Tian ... - 《Web Information Systems Engineering - WISE 2024,Part III》 - International Conference on Web Information Systems Engineering - 2025, - 148～163 - 共16页

摘要： limitations, we propose a Multi-Behavior* Multi-Scale Time* | modeling, a multi-behavior-item heterogeneous graph for | internet era, sequential recommendation* systems have been* | Interval (MB-MSTI) method. This paper involves a multi | Amidst the exponential increase of data in the

关键词： Multi-behavior | Heterogeneous graph neural networks | Sequential recommendation systems

8. Mining Historical Multi-behavior Sequential Patterns for e-Commerce Recommendation NSTL国家科技图书文献中心

S. Bandreddy | C. I. Ezeife ... - 《Information Integration and Web Intelligence,Part II》 - International Conference on Information Integration and Web Intelligence - 2025, - 55～74 - 共20页

摘要： recommendation systems. This paper proposes a Multi-behavior | further capture item-level user multi-behavior | multi-behavior interactions, they are not sequential | ' multi-behavior* patterns to enhance the quality of the* | improving recommendation accuracy. MBSPRec creates a Multi

关键词： Data mining | Sequential pattern mining | Collaborative filtering | Multi-behavior recommender system | E-commerce recommender systems

9. Multi-Behavior Hypergraph Contrastive Learning for Session-Based Recommendation NSTL国家科技图书文献中心

Liangmin Guo | Shiming Zhou ... - 《IEEE Transactions on Knowledge and Data Engineering》 - 2025,37(3) - 1325～1338 - 共14页

摘要：. To address these issues, a multi-behavior | target behavior, ignoring the user's hidden preferences | behavior sequences. It employs contrastive learning to | -supervised signal is created by constructing a multi | -behavior* line graph, enhancing the global session*

关键词： Correlation | Contrastive learning | Accuracy | Feature extraction | Noise | Data models | Data mining | Vectors | History | Hands

10. Causal Behavior Pattern Inference for News Recommendation Through Multi-interest Matching NSTL国家科技图书文献中心

Xingming Chen | Wenqi Fan ... - 《Web Information Systems Engineering - WISE 2024,Part III》 - International Conference on Web Information Systems Engineering - 2025, - 179～190 - 共12页

摘要：Personalized news recommendation* is essential* | conventional sequential recommendation, users' browsing | Causal Behavior* Pattern Inference (CBPI), a framework* | that models user behavior* from a causal perspective* | for helping users efficiently discover content

摘要： for recommendation. Multi-behavior recommendation | Learning for Multi-Behavior* Recommendation (GCLMBR* | improve recommendation performance. Most existing multi | -behavior* recommendation methods are usually insufficient* | multi-behavior data, and integrate the learned single

关键词： Multi-Behavior recommendation | Graph contrastive learning | Graph convolutional network

摘要：Increasing multiple behavior recommendation | behavior. This article proposes a novel multi-behavior | recommendation model based on contrastive clustering learning | (including behavior-level embedding, instance-level | optimize the embeddings of users and items. In behavior

关键词： Multi-behavior Recommendation | Data Sparsity | Contrastive Learning | Contrastive Clustering Learning

摘要：. However, many existing solutions for multi-behavior | items involved in the multi-behavior* interactions. To* | Convolutional Network (DA-GCN) for the multi-behavior | A well-developed recommendation* system can not* | only leverage multi-typed interactions (such as page

关键词： Multi-Behavior Recommendation | Directed Acyclic Graph | Graph Neural Network

摘要：Multi-behavior graph recommendation systems | novel recommendation framework Multi-behavior | behavior patterns and preferences and handling | Heterogeneous Hypergraph Contrastive Recommendation* (MHHCR* | can simultaneously consider various user behaviors

关键词： Multi-behavior recommendation | Contrastive learning | Graph neural networks

摘要：-behavior* User Intent Recommendation model (MUIR) to* | Session-based recommendation* makes a* | recommendation by exploiting short-term user interaction and | recommendation. Although effective, these methods focus on a | particular behavior* or fail to model the complex*

关键词： Recommendation | Session-based recommendation | Multi-behavior modeling

摘要： (Multi-Modal User Behavior* Graph Neural Network, MMUB* | Existing micro-video recommendation* methods* | multimodal information to enhance the recommendation* effect* | same time, the existing micro-video recommendation | leads to the limitation of the recommendation* results*

关键词： Multi-behavior | Multimodal data | Heterogeneous graph neural networks | Recommendation systems

摘要： limitations, we propose a Multi-Behavior* Multi-Scale Time* | modeling, a multi-behavior-item heterogeneous graph for | internet era, sequential recommendation* systems have been* | Interval (MB-MSTI) method. This paper involves a multi | Amidst the exponential increase of data in the

关键词： Multi-behavior | Heterogeneous graph neural networks | Sequential recommendation systems

摘要： recommendation systems. This paper proposes a Multi-behavior | further capture item-level user multi-behavior | multi-behavior interactions, they are not sequential | ' multi-behavior* patterns to enhance the quality of the* | improving recommendation accuracy. MBSPRec creates a Multi

关键词： Data mining | Sequential pattern mining | Collaborative filtering | Multi-behavior recommender system | E-commerce recommender systems

摘要：. To address these issues, a multi-behavior | target behavior, ignoring the user's hidden preferences | behavior sequences. It employs contrastive learning to | -supervised signal is created by constructing a multi | -behavior* line graph, enhancing the global session*

关键词： Correlation | Contrastive learning | Accuracy | Feature extraction | Noise | Data models | Data mining | Vectors | History | Hands

摘要：Personalized news recommendation* is essential* | conventional sequential recommendation, users' browsing | Causal Behavior* Pattern Inference (CBPI), a framework* | that models user behavior* from a causal perspective* | for helping users efficiently discover content

关键词： Personalized news recommendation | Interest matching | Causal discovery

4008-161-200 800-990-8900

国家科技图书文献中心

摘要： for recommendation. Multi-behavior recommendation | Learning for Multi-Behavior Recommendation (GCLMBR | improve recommendation performance. Most existing multi | -behavior recommendation methods are usually insufficient | multi-behavior data, and integrate the learned single

关键词： Multi-Behavior recommendation | Graph contrastive learning | Graph convolutional network

摘要：Increasing multiple behavior recommendation | behavior. This article proposes a novel multi-behavior | recommendation model based on contrastive clustering learning | (including behavior-level embedding, instance-level | optimize the embeddings of users and items. In behavior

关键词： Multi-behavior Recommendation | Data Sparsity | Contrastive Learning | Contrastive Clustering Learning

摘要：. However, many existing solutions for multi-behavior | items involved in the multi-behavior interactions. To | Convolutional Network (DA-GCN) for the multi-behavior | A well-developed recommendation system can not | only leverage multi-typed interactions (such as page

关键词： Multi-Behavior Recommendation | Directed Acyclic Graph | Graph Neural Network

摘要：Multi-behavior graph recommendation systems | novel recommendation framework Multi-behavior | behavior patterns and preferences and handling | Heterogeneous Hypergraph Contrastive Recommendation (MHHCR | can simultaneously consider various user behaviors

关键词： Multi-behavior recommendation | Contrastive learning | Graph neural networks

摘要：-behavior User Intent Recommendation model (MUIR) to | Session-based recommendation makes a | recommendation by exploiting short-term user interaction and | recommendation. Although effective, these methods focus on a | particular behavior or fail to model the complex

关键词： Recommendation | Session-based recommendation | Multi-behavior modeling

摘要： (Multi-Modal User Behavior Graph Neural Network, MMUB | Existing micro-video recommendation methods | multimodal information to enhance the recommendation effect | same time, the existing micro-video recommendation | leads to the limitation of the recommendation results

关键词： Multi-behavior | Multimodal data | Heterogeneous graph neural networks | Recommendation systems

摘要： limitations, we propose a Multi-Behavior Multi-Scale Time | modeling, a multi-behavior-item heterogeneous graph for | internet era, sequential recommendation systems have been | Interval (MB-MSTI) method. This paper involves a multi | Amidst the exponential increase of data in the

关键词： Multi-behavior | Heterogeneous graph neural networks | Sequential recommendation systems

摘要： recommendation systems. This paper proposes a Multi-behavior | further capture item-level user multi-behavior | multi-behavior interactions, they are not sequential | ' multi-behavior patterns to enhance the quality of the | improving recommendation accuracy. MBSPRec creates a Multi

关键词： Data mining | Sequential pattern mining | Collaborative filtering | Multi-behavior recommender system | E-commerce recommender systems

摘要：. To address these issues, a multi-behavior | target behavior, ignoring the user's hidden preferences | behavior sequences. It employs contrastive learning to | -supervised signal is created by constructing a multi | -behavior line graph, enhancing the global session

关键词： Correlation | Contrastive learning | Accuracy | Feature extraction | Noise | Data models | Data mining | Vectors | History | Hands

摘要：Personalized news recommendation is essential | conventional sequential recommendation, users' browsing | Causal Behavior Pattern Inference (CBPI), a framework | that models user behavior from a causal perspective | for helping users efficiently discover content

关键词： Personalized news recommendation | Interest matching | Causal discovery

4008-161-200 800-990-8900

国家科技图书文献中心

摘要： for recommendation. Multi-behavior recommendation | Learning for Multi-Behavior* Recommendation (GCLMBR* | improve recommendation performance. Most existing multi | -behavior* recommendation methods are usually insufficient* | multi-behavior data, and integrate the learned single

摘要：. However, many existing solutions for multi-behavior | items involved in the multi-behavior* interactions. To* | Convolutional Network (DA-GCN) for the multi-behavior | A well-developed recommendation* system can not* | only leverage multi-typed interactions (such as page

摘要：Multi-behavior graph recommendation systems | novel recommendation framework Multi-behavior | behavior patterns and preferences and handling | Heterogeneous Hypergraph Contrastive Recommendation* (MHHCR* | can simultaneously consider various user behaviors

摘要：-behavior* User Intent Recommendation model (MUIR) to* | Session-based recommendation* makes a* | recommendation by exploiting short-term user interaction and | recommendation. Although effective, these methods focus on a | particular behavior* or fail to model the complex*

摘要： (Multi-Modal User Behavior* Graph Neural Network, MMUB* | Existing micro-video recommendation* methods* | multimodal information to enhance the recommendation* effect* | same time, the existing micro-video recommendation | leads to the limitation of the recommendation* results*

摘要： limitations, we propose a Multi-Behavior* Multi-Scale Time* | modeling, a multi-behavior-item heterogeneous graph for | internet era, sequential recommendation* systems have been* | Interval (MB-MSTI) method. This paper involves a multi | Amidst the exponential increase of data in the

摘要： recommendation systems. This paper proposes a Multi-behavior | further capture item-level user multi-behavior | multi-behavior interactions, they are not sequential | ' multi-behavior* patterns to enhance the quality of the* | improving recommendation accuracy. MBSPRec creates a Multi

摘要：. To address these issues, a multi-behavior | target behavior, ignoring the user's hidden preferences | behavior sequences. It employs contrastive learning to | -supervised signal is created by constructing a multi | -behavior* line graph, enhancing the global session*

摘要：Personalized news recommendation* is essential* | conventional sequential recommendation, users' browsing | Causal Behavior* Pattern Inference (CBPI), a framework* | that models user behavior* from a causal perspective* | for helping users efficiently discover content