A5031849216- Complex Network Analysis Techniques
- Misinformation and Its Impacts
- Advanced Graph Neural Networks
- Opinion Dynamics and Social Influence
- Bioinformatics and Genomic Networks
- Risk and Safety Analysis
- Topic Modeling
- Multi-Criteria Decision Making
- Data-Driven Disease Surveillance
- Text and Document Classification Technologies
- Software Reliability and Analysis Research
- Cognitive Science and Mapping
- Explainable Artificial Intelligence (XAI)
- Advanced Decision-Making Techniques
- Machine Learning and Data Classification
- Computational and Text Analysis Methods
- Biomedical Text Mining and Ontologies
- Machine Learning in Materials Science
- Adversarial Robustness in Machine Learning
- Graph theory and applications
- Computational Drug Discovery Methods
- Advanced Text Analysis Techniques
- Quality Function Deployment in Product Design
- Reliability and Maintenance Optimization
Tianjin Medical University
2025
Tianjin Medical University Eye Hospital
2025
Chinese University of Hong Kong
2023-2024
Tsinghua University
2020
Southwest University
2017-2018
University of Electronic Science and Technology of China
2018
Social media has been developing rapidly in public due to its nature of spreading new information, which leads rumors being circulated. Meanwhile, detecting from such massive information social is becoming an arduous challenge. Therefore, some deep learning methods are applied discover through the way they spread, as Recursive Neural Network (RvNN) and so on. However, these only take into account patterns propagation but ignore structures wide dispersion rumor detection. Actually, two...
Abstract Failure mode and effects analysis (FMEA) is a widely used technique for assessing the risk of potential failure modes in designs, products, processes, system, services. One main problems with FMEA need to address variety assessments given by team members sequence according degree factors. Many different methods have been proposed improve traditional FMEA, which impractical when multiple experts one are imprecise, incomplete, or inconsistent. However, existing cannot adequately...
In the field of complex networks, how to identify influential nodes is a significant issue in analyzing structure network. existing method proposed based on local dimension, global information networks not taken into consideration. this paper, node dimension by synthesizing dimensions at different topological distance scales. A case study Netscience network used illustrate efficiency and practicability method.
Primary glaucoma patients faced many difficulties that affected their treatment during the COVID-19 pandemic. Glaucoma often starts with prescription eye-drops. However, delays in ophthalmic therapy occur due to poor awareness of dangers glaucoma, which subsequently leads irreversible visual field defects and eventual blindness. This study aimed explore social, personal medical factors contributed barriers primary pandemic, overarching goal providing insights develop measures can identify...
Social media has been developing rapidly in public due to its nature of spreading new information, which leads rumors being circulated. Meanwhile, detecting from such massive information social is becoming an arduous challenge. Therefore, some deep learning methods are applied discover through the way they spread, as Recursive Neural Network (RvNN) and so on. However, these only take into account patterns propagation but ignore structures wide dispersion rumor detection. Actually, two...
Graph neural networks (GNNs) have achieved tremendous success in the task of graph classification and its diverse downstream real-world applications. Despite huge learning representations, current GNN models demonstrated their vulnerability to potentially existent adversarial examples on graph-structured data. Existing approaches are either limited structure attacks or restricted local informatio, urging for design a more general attack framework classification, which faces significant...
Recently, generative models based on the diffusion process have emerged as a promising direction for automating design of molecules. However, directly adding continuous Gaussian noise to discrete graphs leads problem that generated data do not conform graph distribution in training set. Current either corrupt through transition matrix or relax space process. These approaches make it hard perform extensible conditional generation, such adapting text-based conditions, due lack embedding...
Graph Identification (GI) has long been researched in graph learning and is essential certain applications (e.g. social community detection). Specifically, GI requires to predict the label/score of a target given its collection node features edge connections. While this task common, more complex cases arise practice---we are supposed do inverse thing by, for example, grouping similar users network labels different communities. This triggers an interesting thought: can we identify nodes...