A5023510892- Advanced Graph Neural Networks
- Advanced Computing and Algorithms
- Domain Adaptation and Few-Shot Learning
- Complex Network Analysis Techniques
- Recommender Systems and Techniques
- Face and Expression Recognition
- Advanced Image and Video Retrieval Techniques
- Brain Tumor Detection and Classification
- Geochemistry and Elemental Analysis
- Extraction and Separation Processes
- Remote-Sensing Image Classification
- Human Pose and Action Recognition
- Microplastics and Plastic Pollution
- Text and Document Classification Technologies
- Video Surveillance and Tracking Methods
- Recycling and Waste Management Techniques
- Radioactive element chemistry and processing
- Image Retrieval and Classification Techniques
- Additive Manufacturing and 3D Printing Technologies
- Adsorption and biosorption for pollutant removal
- Topic Modeling
- Machine Learning and ELM
- Effects of Radiation Exposure
- Data Stream Mining Techniques
- Graph Theory and Algorithms
Fuzhou University
2021-2025
Shenzhen Research Institute of Big Data
2024
Chinese University of Hong Kong, Shenzhen
2024
Harbin Institute of Technology
2024
Longhua Hospital Shanghai University of Traditional Chinese Medicine
2024
Shanghai University of Traditional Chinese Medicine
2024
As real-world data become increasingly heterogeneous, multi-view semi-supervised learning has garnered widespread attention. Although existing studies have made efforts towards this and achieved decent performance, they are restricted to shallow models how mine deeper information from multiple views remains be investigated. a recently emerged neural network, Graph Convolutional Network (GCN) exploits graph structure propagate label signals encouraging it been widely employed in various...
Multi-view learning is a promising research field that aims to enhance performance by integrating information from diverse data perspectives. Due the increasing interest in graph neural networks, researchers have gradually incorporated various models into multi-view learning. Despite significant progress, current methods face challenges extracting multiple graphs while simultaneously accommodating specific downstream tasks. Additionally, lack of subsequent refinement process for learned...
Graph convolutional network (GCN) with the powerful capacity to explore graph-structural data has gained noticeable success in recent years. Nonetheless, most of existing GCN-based models suffer from notorious over-smoothing issue, owing which shallow networks are extensively adopted. This may be problematic for complex graph datasets because a deeper GCN should beneficial propagating information across remote neighbors. Recent works have devoted effort addressing problems, including...
Graph Neural Networks (GNNs) have exhibited remarkable capabilities for dealing with graph-structured data. However, recent studies revealed their fragility to adversarial attacks, where imperceptible perturbations the graph structure can easily mislead predictions. To enhance robustness, some methods attempt learn robust representation through improving GNN architectures. Subsequently, another approach suggests that these GNNs might taint feature information and poor classifier performance,...
Uranium is a basic and strategic resource related to national development security. The uranium resources contained in the ocean are thousands of times that land, up about 4.5 billion tons. However, it still severe challenge for extraction from seawater as contains trace amounts large number cations. Herein, new material, phosphate-functionalized collagen fibers, was prepared by "covalent cross-linking" method grafting phosphate functional groups onto surface fibers (CF) with multihierarchy...
Existing multi-view graph learning methods often rely on consistent information for similar nodes within and across views, however they may lack adaptability when facing diversity challenges from noise, varied complex data distributions. These can be mainly categorized into: 1) View-specific intra-view noise incomplete information; 2) Cross-view inter-view caused by various latent semantics; 3) Cross-group inter-group due to distribution differences. To this end, we propose a universal...
Graph convolutional network (GCN) has gained widespread attention in semisupervised classification tasks. Recent studies show that GCN-based methods have achieved decent performance numerous fields. However, most of the existing generally adopted a fixed graph cannot dynamically capture both local and global relationships. This is because hidden important relationships may not be directed exhibited structure, causing degraded Moreover, missing noisy data yielded by result wrong connections,...