A5013514822- Structural Health Monitoring Techniques
- Synthesis and biological activity
- Computational Drug Discovery Methods
- Misinformation and Its Impacts
- Spam and Phishing Detection
- Concrete Corrosion and Durability
- Species Distribution and Climate Change
- Masonry and Concrete Structural Analysis
- Human Mobility and Location-Based Analysis
- Image and Object Detection Techniques
- Remote Sensing and LiDAR Applications
- Data Management and Algorithms
- Advanced ceramic materials synthesis
- Industrial Vision Systems and Defect Detection
- Advanced Graph Neural Networks
- Innovative concrete reinforcement materials
- Structural Engineering and Vibration Analysis
- History and advancements in chemistry
- Topic Modeling
- Complex Network Analysis Techniques
- 3D Surveying and Cultural Heritage
- Seismic Performance and Analysis
- Concrete and Cement Materials Research
- Advanced Neural Network Applications
- Traffic Prediction and Management Techniques
Zhejiang Lab
2023-2025
Zhengzhou University
2023-2024
Stanford University
2023
Southwest Forestry University
2022
Fake news detection on social media is crucial to purifying the online environment and protecting public safety. Many existing methods explore propagation structures through graph neural networks (GNNs) determine truthfulness of news. End-to-end supervised GNNs notoriously depend large amounts labels. Recently, self-supervised pretraining has been a promising solution alleviate dependence However, application in fake still suffers from two challenges: 1) missing unreliable interactions...
Denoising diffusion models have shown great potential in multiple research areas. Existing diffusion-based generative methods on de novo 3D molecule generation face two major challenges. Since majority heavy atoms molecules allow connections to through single bonds, solely using pair-wise distance model geometries is insufficient. Therefore, the first one involves proposing an effective neural network as denoising kernel that capable capture complex multi-body interatomic relationships and...
Abstract Motivation:: The prediction of cancer drug response is a challenging subject in modern personalized therapy due to the uncertainty efficacy and heterogeneity patients. It has been shown that characteristics itself genomic patient can greatly influence results response. Therefore, accurate, efficient, comprehensive methods for feature extraction genomics integration are crucial improve accuracy. Results:: Accurate vital guiding design anticancer drugs. In this study, we propose an...
Next destination recommendation is a crucial research area for understanding human travel behavior. However, existing studies often overlook the problem of underfitting, which arises due to limited regularity in users' patterns. To tackle this issue, we leverage diverse co-occurrence patterns (CoPs) discover potential user preferences. These capture intersections with similar spatial and temporal characteristics travels. traditional graph neural network (GNN)-based approaches struggle...
Self-supervised learning (SSL) has become one of the most popular paradigms and achieved remarkable success in graph field. Recently, a series pre-training studies on heterogeneous graphs (HGs) using SSL have been proposed considering heterogeneity real-world data. However, verification robustness is still research gap. Most existing researches focus supervised attacks graphs, which are limited to specific scenario will not work when labels available. In this paper, we propose novel...
<title>Abstract</title> The study is directed toward the precise prediction of fundamental period steel-braced Reinforced Concrete (RC) Moment-Resisting Frames (MRFs) through utilization stacked generalization, an advanced algorithmic ensemble machine learning technique. To facilitate this, a meticulously curated database comprising 17,280 building models has been automated using ETABS Application Programming Interface (API). encompasses both Concentrically Braced (CBFs) and Eccentrically...
Abstract Motivation: The prediction of cancer drug response is a challenging subject in modern personalized therapy due to the uncertainty efficacy and heterogeneity patients. It has been shown that characteristics itself genomic patient can greatly influence results response. Therefore, accurate, efficient, comprehensive methods for feature extraction genomics integration are crucial improve accuracy. Results: Accurate vital guiding design anticancer drugs. In this study, we propose an...