NSTL国家科技图书文献中心

1. Dual-View Desynchronization Hypergraph Learning for Dynamic Hyperedge Prediction NSTL国家科技图书文献中心

Zhihui Wang | Jianrui Chen ... - 《IEEE Transactions on Knowledge and Data Engineering》 - 2025,37(2) - 597～612 - 共16页

摘要： hypergraph learning for arbitrary-order Dynamic Hyperedge | multiple individuals. Due to the necessity of hypergraph | separately through an elastic hypergraph* neural network* | Hyperedges, as extensions of pairwise edges | , can characterize higher-order relations among

关键词： Feature extraction | Predictive models | Representation learning | Decoding | Contrastive learning | Biological neural networks | Analytical models | Aggregates | Transforms | Training

2. Cost-Sensitive Hypergraph Learning With Structure Quality Preservation for IoT Software Defect Prediction NSTL国家科技图书文献中心

Nan Wang | Jiqiang Liu ... - 《IEEE Open Journal of the Communications Society》 - 2025,6 - 2780～2791 - 共12页

摘要：, we propose a cost-sensitive hypergraph learning | hypergraph structure instead of graph structure to model | that if a cost-sensitive hypergraph* has a high* | margin cost-sensitive hypergraph* while avoiding using* | of a cost-sensitive hypergraph* with a small margin*

关键词： Software | Costs | Software engineering | Software measurement | Software algorithms | Mathematical models | Generative AI | Feature extraction | Ensemble learning | Correlation

3. Multi-task Learning of Heterogeneous Hypergraph Representations in LBSNs NSTL国家科技图书文献中心

Dong Duc Anh Nguyen | Minh Hieu Nguyen ... - 《Advanced Data Mining and Applications,Part III》 - International Conference on Advanced Data Mining and Applications - 2025, - 161～177 - 共17页

摘要： representation learning* often consider LBSNs to be either* | hypergraphs. As a potential solution, hypergraph* convolution* | of convolution to representation learning* in an* | representation learning* by leveraging the power of multi-task* | learning. By jointly optimizing both friendship

关键词： Location-based social networks | Heterogeneous hypergraph learning | Multi-task learning | Graph neural networks

4. Heterogeneous Hypergraph Polynomial Learning for Herb Recommendation NSTL国家科技图书文献中心

Yao Xiao | Jin Liu ... - 《Database Systems for Advanced Applications,Part III》 - International Conference on Database Systems for Advanced Applications | International Workshop on Big Data Management and Service | International Workshop on Graph Data Management and Analysis | International Workshop on Big Data Quality Management | Workshop on Emerging Results inData Science and Engineering - 2025, - 313～322 - 共10页

摘要： Heterogeneous Hypergraph* Polynomial Learning (HPPL). First, we* | existing graph representation learning* methods obtain* | construct the heterogeneous hypergraph* according to the* | learning framework to replace the Laplacian decomposition | Herb recommendation aims to recommend a set of

关键词： Herb recommendation | Traditional chinese medicine | Heterogeneous hypergraph | Representation learning

5. Salient event detection via hypergraph convolutional network with cross-view self-supervised learning NSTL国家科技图书文献中心

Zhu E. | Yu Z.... - 《Neurocomputing》 - 2025,612(Jan.7) - 1.1～1.13 - 共13页

摘要： via Hypergraph* Convolutional Network with Graph Self* | -supervised Learning* (SEDGS). More specifically, we first* | hypergraph convolutional network to model the event context | enhance hypergraph* modeling and ensure consistency* | representations, we employ contrastive self-supervised learning

关键词： Event representation | Graph neural network | Hypergraph learning | Salient event detection | Self-supervised learning

6. Physics-Guided Hypergraph Contrastive Learning for Dynamic Hyperedge Prediction NSTL国家科技图书文献中心

Zhihui Wang | Jianrui Chen ... - 《IEEE transactions on network science and engineering》 - 2025,12(1) - 433～450 - 共18页

摘要： hypergraph contrastive learning involve augmentation | , a physics-guided hypergraph contrastive learning | -order and lower-order views carried by the hypergraph | views of the hypergraph to perform dynamic hypergraph | contrastive learning* and obtain abstract and concrete*

关键词： Contrastive learning | Predictive models | Optimization | Computational modeling | Training | Representation learning | Feature extraction | Mathematical models | Adaptation models | Neurons

7. Interactive multi-hypergraph inferring and channel-enhanced and attribute-enhanced learning for drug-related side effect prediction NSTL国家科技图书文献中心

Xuan P. | Wu S.... - 《Computers in Biology and Medicine》 - 2025,184 - 109321～109321 - 共10页

摘要： interactive multi-hypergraph* inferring and channel-enhanced* | and attribute-enhanced learning, ICAL, was proposed | channels and attributes. First, we designed a hypergraph | drugs and side effects, and the entire hypergraph | similarities, and each hypergraph* implies its specific*

关键词： Attention at attribute level | Attribute-enhanced learning | Channel-enhanced learning | Drug-side effect association prediction | Interactive multi-hypergraph inferring

8. 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： hypergraph contrastive learning model for session-based | behavior sequences. It employs contrastive learning* to* | hypergraph is designed for the current session to capture | Most current session-based recommendations | model session sequences solely based on the user's

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

9. Hyper-3DG: Text-to-3D Gaussian Generation via Hypergraph NSTL国家科技图书文献中心

Donglin,Di | Jiahui,Yang ... - 《International Journal of Computer Vision》 - 2025,133(5) - 2886～2909 - 共24页

摘要：-3DGS Hypergraph* Learning on both explicit attributes* | “3D Gaussian Generation via Hypergraph* (Hyper-3DG* | module, named “Geometry and Texture Hypergraph* Refiner* | Abstract Text-to-3D generation represents an | exciting field that has seen rapid advancements

关键词： Text-to-3D generation | 3D Gaussian Splatting | Hypergraph learning

10. Hypergraph Self-Supervised Learning-Based Joint Spectral-Spatial-Temporal Feature Representation for Hyperspectral Image Change Detection NSTL国家科技图书文献中心

Ping Jian | Yimin Ou ... - 《IEEE journal of selected topics in applied earth observations and remote sensing》 - 2025,18 - 741～756 - 共16页

摘要： proposes a hypergraph* self-supervised learning (HG-SSL* | Deep learning* has shown promising performance* | -spatial features learning* and generative temporal* | features learning* are skillfully designed to exploit the* | inherent characteristics of hypergraph* models and extract*

关键词： Feature extraction | Correlation | Transformers | Data models | Mathematical models | Contrastive learning | Representation learning | Principal component analysis | Manuals | Image reconstruction

摘要： hypergraph learning for arbitrary-order Dynamic Hyperedge | multiple individuals. Due to the necessity of hypergraph | separately through an elastic hypergraph neural network | Hyperedges, as extensions of pairwise edges | , can characterize higher-order relations among

关键词： Feature extraction | Predictive models | Representation learning | Decoding | Contrastive learning | Biological neural networks | Analytical models | Aggregates | Transforms | Training

摘要：, we propose a cost-sensitive hypergraph learning | hypergraph structure instead of graph structure to model | that if a cost-sensitive hypergraph has a high | margin cost-sensitive hypergraph while avoiding using | of a cost-sensitive hypergraph with a small margin

关键词： Software | Costs | Software engineering | Software measurement | Software algorithms | Mathematical models | Generative AI | Feature extraction | Ensemble learning | Correlation

摘要： representation learning often consider LBSNs to be either | hypergraphs. As a potential solution, hypergraph convolution | of convolution to representation learning in an | representation learning by leveraging the power of multi-task | learning. By jointly optimizing both friendship

关键词： Location-based social networks | Heterogeneous hypergraph learning | Multi-task learning | Graph neural networks

摘要： Heterogeneous Hypergraph Polynomial Learning (HPPL). First, we | existing graph representation learning methods obtain | construct the heterogeneous hypergraph according to the | learning framework to replace the Laplacian decomposition | Herb recommendation aims to recommend a set of

关键词： Herb recommendation | Traditional chinese medicine | Heterogeneous hypergraph | Representation learning

关键词： Event representation | Graph neural network | Hypergraph learning | Salient event detection | Self-supervised learning

摘要： hypergraph contrastive learning involve augmentation | , a physics-guided hypergraph contrastive learning | -order and lower-order views carried by the hypergraph | views of the hypergraph to perform dynamic hypergraph | contrastive learning and obtain abstract and concrete

关键词： Contrastive learning | Predictive models | Optimization | Computational modeling | Training | Representation learning | Feature extraction | Mathematical models | Adaptation models | Neurons

摘要： interactive multi-hypergraph inferring and channel-enhanced | and attribute-enhanced learning, ICAL, was proposed | channels and attributes. First, we designed a hypergraph | drugs and side effects, and the entire hypergraph | similarities, and each hypergraph implies its specific

关键词： Attention at attribute level | Attribute-enhanced learning | Channel-enhanced learning | Drug-side effect association prediction | Interactive multi-hypergraph inferring

摘要： hypergraph contrastive learning model for session-based | behavior sequences. It employs contrastive learning to | hypergraph is designed for the current session to capture | Most current session-based recommendations | model session sequences solely based on the user's

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

摘要：-3DGS Hypergraph Learning on both explicit attributes | “3D Gaussian Generation via Hypergraph (Hyper-3DG | module, named “Geometry and Texture Hypergraph Refiner | Abstract Text-to-3D generation represents an | exciting field that has seen rapid advancements

关键词： Text-to-3D generation | 3D Gaussian Splatting | Hypergraph learning

摘要： proposes a hypergraph self-supervised learning (HG-SSL | Deep learning has shown promising performance | -spatial features learning and generative temporal | features learning are skillfully designed to exploit the | inherent characteristics of hypergraph models and extract

关键词： Feature extraction | Correlation | Transformers | Data models | Mathematical models | Contrastive learning | Representation learning | Principal component analysis | Manuals | Image reconstruction

4008-161-200 800-990-8900

国家科技图书文献中心

摘要： hypergraph learning for arbitrary-order Dynamic Hyperedge | multiple individuals. Due to the necessity of hypergraph | separately through an elastic hypergraph* neural network* | Hyperedges, as extensions of pairwise edges | , can characterize higher-order relations among

摘要：, we propose a cost-sensitive hypergraph learning | hypergraph structure instead of graph structure to model | that if a cost-sensitive hypergraph* has a high* | margin cost-sensitive hypergraph* while avoiding using* | of a cost-sensitive hypergraph* with a small margin*

摘要： hypergraph contrastive learning involve augmentation | , a physics-guided hypergraph contrastive learning | -order and lower-order views carried by the hypergraph | views of the hypergraph to perform dynamic hypergraph | contrastive learning* and obtain abstract and concrete*

摘要： interactive multi-hypergraph* inferring and channel-enhanced* | and attribute-enhanced learning, ICAL, was proposed | channels and attributes. First, we designed a hypergraph | drugs and side effects, and the entire hypergraph | similarities, and each hypergraph* implies its specific*

摘要： hypergraph contrastive learning model for session-based | behavior sequences. It employs contrastive learning* to* | hypergraph is designed for the current session to capture | Most current session-based recommendations | model session sequences solely based on the user's

摘要：-3DGS Hypergraph* Learning on both explicit attributes* | “3D Gaussian Generation via Hypergraph* (Hyper-3DG* | module, named “Geometry and Texture Hypergraph* Refiner* | Abstract Text-to-3D generation represents an | exciting field that has seen rapid advancements

摘要： proposes a hypergraph* self-supervised learning (HG-SSL* | Deep learning* has shown promising performance* | -spatial features learning* and generative temporal* | features learning* are skillfully designed to exploit the* | inherent characteristics of hypergraph* models and extract*