A5101362670- Advanced Graph Neural Networks
- Topic Modeling
- Recommender Systems and Techniques
- Imbalanced Data Classification Techniques
- Brain Tumor Detection and Classification
- Artificial Intelligence in Healthcare
- Healthcare Systems and Reforms
- Complex Network Analysis Techniques
- Computational Drug Discovery Methods
- Natural Language Processing Techniques
- Software Engineering Research
- Chemical Synthesis and Analysis
- Graph Theory and Algorithms
- Machine Learning in Materials Science
Xiamen University of Technology
2024-2025
Health insurance fraud is becoming more common and impacting the fairness sustainability of health system. Traditional detection primarily relies on recognizing established data patterns. However, with ever-expanding complex nature data, it difficult for these traditional methods to effectively capture evolving fraudulent activity tactics keep pace constant improvements innovations fraudsters. As a result, there an urgent need accurate flexible analytics detect potential fraud. To address...
<title>Abstract</title> Graph Convolutional Networks (GCNs) is a dominant approach for graph representation learning through neighborhood aggregation.However, existing GCN methods rely on single structural view that only captures direct connections. This limitation overlooks important long-range dependencies and global topological patterns, leading to suboptimal node representations downstream tasks. To address these limitations, we propose Multi-Block Network (MBGCN) constructs two...
Accurately predicting Drug-Drug Interaction (DDI) is a critical and challenging aspect of the drug discovery process, particularly in preventing adverse reactions patients undergoing combination therapy. However, current DDI prediction methods often overlook interaction information between chemical substructures drugs, focusing solely on drugs failing to capture sufficient substructure details. To address this limitation, we introduce novel method: Multi-layer Adaptive Soft Mask Graph Neural...
In previous research, the prevailing assumption was that Graph Neural Networks (GNNs) precisely depicted interconnections among nodes within graph's architecture. Nonetheless, real-world graph datasets are often rife with noise, elements can disseminate through network and ultimately affect outcome of downstream tasks. Facing complex fabric graphs myriad potential disturbances, we introduce Sparse Dynamic Attention (SDGAT) in this research. SDGAT employs L0 regularization technique to...