A5084849129- Advanced Graph Neural Networks
- Advanced Computing and Algorithms
- Face and Expression Recognition
- Topic Modeling
- Complex Network Analysis Techniques
- Recommender Systems and Techniques
- Text and Document Classification Technologies
- Image Retrieval and Classification Techniques
- Advanced Image and Video Retrieval Techniques
- Video Surveillance and Tracking Methods
- Remote-Sensing Image Classification
- Sparse and Compressive Sensing Techniques
- Domain Adaptation and Few-Shot Learning
- Graph Theory and Algorithms
- Animal Disease Management and Epidemiology
- Natural Language Processing Techniques
- Influenza Virus Research Studies
- Advanced Battery Technologies Research
- Infection Control and Ventilation
- Machine Learning and ELM
- Advanced DC-DC Converters
- Indoor Air Quality and Microbial Exposure
- Multimodal Machine Learning Applications
- Brain Tumor Detection and Classification
- Osteoarthritis Treatment and Mechanisms
Hebei Agricultural University
2022-2025
Hong Kong Baptist University
2024-2025
Inspur (China)
2023-2025
Chinese Academy of Agricultural Sciences
2022-2025
Jilin University
2025
Fuzhou University
2020-2024
Emory University
2024
Shanghai Institute of Technology
2024
Heilongjiang University of Chinese Medicine
2024
South China University of Technology
2021-2022
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...
Sparsity-constrained optimization problems are common in machine learning, such as sparse coding, low-rank minimization and compressive sensing. However, most of previous studies focused on constructing various hand-crafted regularizers, while little work was devoted to learning adaptive regularizers from given input data for specific tasks. In this paper, we propose a deep regularizer model that learns data-driven adaptively. Via the proximal gradient algorithm, find is equivalent...
Deep multi-view representation learning focuses on training a unified low-dimensional for data with multiple sources or modalities. With the rapidly growing attention of graph neural networks, more and researchers have introduced various models into learning. Although considerable achievements been made, most existing methods usually propagate information in single view fuse only from perspective attributes relationships. To solve aforementioned problems, we propose an efficient model termed...
Multi-view subspace clustering aims to utilize the comprehensive information of multi-source features aggregate data into multiple subspaces. Recently, low-rank tensor learning has been applied multi-view clustering, which explores high-order correlations and achieved remarkable results. However, these existing methods have certain limitations: 1) The processes label indicator matrix are independent. 2) Variable contributions different views consistent results not discriminated. To handle...
Accumulating evidence indicates that the long noncoding RNA, TINCR, plays a critical role in cancer progression and metastasis. However, overall biological mechanisms of TINCR were involved human gastric (GC) remain largely unknown.TINCR expression was measured 56 paired tumor adjacent nontumor tissue samples by real-time polymerase chain reaction (PCR). Insights mechanism competitive endogenous RNAs (ceRNAs) gained from bioinformatic analysis, luciferase assays. The effects miR-375 on GC...
Deep multi-view clustering utilizes neural networks to extract the potential peculiarities of complementarity and consistency information among features. This can obtain a consistent representation that improves performance. Although multitude deep approaches have been proposed, most lack theoretic interpretability while maintaining advantages good In this paper, we propose an effective differentiable network with alternating iterative optimization for co-clustering termed bi-sparse (DBMC)...
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...
Semi-supervised node classification with Graph Convolutional Network (GCN) is an attractive topic in social media analysis and applications. Recent studies show that GCN-based methods can facilitate the accuracy increase of learning algorithms. However, most existing do not conduct adequate explorations complementary information within topology structure. Besides, they also suffer from insufficient excavation useful among nodes scarcity labeled samples, resulting undesired performance. To...
To date, intermediate hosts of SARS-CoV-2 remain obscure and controversial. Several studies have shown that SARS-CoV-2-related pangolin coronavirus (Pangolin-CoV) has a high sequence similarity to might be the initial source SARS-CoV-2; however, biological characteristics Pangolin-CoV are still largely unknown. In this study, we evaluated pathogenicity transmissibility in Syrian golden hamsters Mesocricetus auratus (Linnaeus, 1758) compared it with SARS-CoV-2. could effectively infect...
Influenza virus is a serious threat to global human health and public security. There an urgent need develop new anti-influenza drugs. Lentinan (LNT) has attracted increasing attention in recent years. As potential protective agent, LNT been shown have anti-tumor, anti-inflammatory, antiviral properties. However, there no further research into the action of lentinan vivo , mechanism still not fully understood. In this study, effect were studied Institute Cancer Research (ICR) mouse model....
With the development of modern pig raising technology, increasing density animals in houses leads to accumulation microbial aerosols houses. It is an important prerequisite grasp characteristics bacteria different solve problems air pollution and disease prevention control This work investigated effects growth stages on bacterial aerosol concentrations communities Three traditional types closed were studied: farrowing (FAR) houses, weaning (WEA) fattening (FAT) The Andersen six-stage sampler...
Introduction Influenza A viruses (IAVs) are important pathogens of respiratory infections, causing not only seasonal influenza but also pandemics and posing a global threat to public health. IAVs infection spreads rapidly, widely, across species, huge losses, especially zoonotic infections that more harmful. Fast sensitive detection is critical for controlling the spread this disease. Methods Here, real-time reverse transcription recombinase-aided amplification (real-time RT-RAA) assay...
Due to the powerful capability gather information of neighborhood nodes, Graph Convolutional Network (GCN) has become a widely explored hotspot in recent years. As well-established extension, AutoEncoder (GAE) succeeds mining underlying node representations via evaluating quality adjacency matrix reconstruction from learned features. However, limited works on GAE were devoted leveraging both semantic and topological graphs, they only indirectly extracted relationships between graphs weights...
Multi-view data containing complementary and consensus information can facilitate representation learning by exploiting the intact integration of multi-view features. Because most objects in real world often have underlying connections, organizing as heterogeneous graphs is beneficial to extracting latent among different objects. Due powerful capability gather neighborhood nodes, this article, we apply Graph Convolutional Network (GCN) cope with graph originating from data, which still...