A5101536504- Advanced Graph Neural Networks
- Complex Network Analysis Techniques
- Graph Theory and Algorithms
- Transportation Planning and Optimization
- Text and Document Classification Technologies
- Recommender Systems and Techniques
- Traffic Prediction and Management Techniques
- Spam and Phishing Detection
- Internet Traffic Analysis and Secure E-voting
- Human Mobility and Location-Based Analysis
Hong Kong Polytechnic University
2023-2024
Inner Mongolia University
2024
Changchun University of Science and Technology
2024
Graph neural networks (GNNs) have received remarkable success in link prediction (GNNLP) tasks. Existing efforts first predefine the subgraph for whole dataset and then apply GNNs to encode edge representations by leveraging neighborhood structure induced fixed subgraph. The prominence of GNNLP methods significantly relies on adhoc Since node connectivity real-world graphs is complex, one shared limited all edges. Thus, choices subgraphs should be personalized different However, performing...
Graph contrastive learning (GCL) has emerged as an effective tool to learn representations for whole graphs in the absence of labels. The key idea is maximize agreement between two augmented views each graph via data augmentation. Existing GCL models mainly focus on applying identical augmentation strategies all within a given scenario. However, real-world are often not monomorphic but abstractions diverse natures. Even same scenario (e.g., macromolecules and online communities), different...
Graph neural networks (GNNs) have shown prominent performance on attributed network embedding. However, existing efforts mainly focus exploiting structures, while the exploitation of node attributes is rather limited as they only serve features at initial layer. This simple strategy impedes potential in augmenting connections, leading to receptive field for inactive nodes with few or even no neighbors. Furthermore, training objectives (i.e., reconstructing structures) most GNNs also do not...
Shared bikes, as an eco-friendly transport mode, facilitate short commutes for urban dwellers and help alleviate traffic. However, the prevalent station-based strategy bike placements often overlooks zones, cycling patterns, more, resulting in underutilized bikes. To address this, we introduce Spatio-Temporal Bike-sharing Demand Prediction (ST-BDP) model, leveraging multi-source data Graph Convolutional Networks (STGCN). This model predicts spatial user demand bikes between stations by...
Graph neural networks (GNNs) have become the de-facto standard for learning on graphs. GNNs involve a recursive message passing mechanism to recursively aggregate messages from adjacent nodes. It is in line with topological structures and has dominated implementation of existing GNN models. However, it causes critical issue, i.e., high-order neighbors must be transmitted layer by layer. Important node could trivial its low-order neighbors, which corrupts long-range messages. In this paper,...