A5051713264- Advanced Graph Neural Networks
- Artificial Intelligence in Healthcare
- Anomaly Detection Techniques and Applications
- Domain Adaptation and Few-Shot Learning
- Machine Learning and Data Classification
- Neural Networks and Applications
- Advanced Neural Network Applications
- Topic Modeling
- Complex Network Analysis Techniques
- Brain Tumor Detection and Classification
- Data Mining Algorithms and Applications
Beijing University of Posts and Telecommunications
2021-2024
Heterogeneous graphs (HGs), consisting of multiple types nodes and links, can characterize a variety real-world complex systems. Recently, heterogeneous graph neural networks (HGNNs), as powerful embedding method to aggregate structure attribute information, has earned lot attention. Despite the ability HGNNs in capturing rich semantics which reveal different aspects nodes, they still stay at coarse-grained level simply exploits structural characteristics. In fact, unstructured text content...
Out-of-distribution (OOD) detection, which aims to identify OOD samples from in-distribution (ID) ones in test time, has become an essential problem machine learning. However, existing works are mostly conducted on Euclidean data, and the graph-structured data remains under-explored. Several recent begin study graph but they all need train a neural network (GNN) scratch with high computational cost. In this work, we make first attempt endow well-trained GNN detection ability without...
Graph Neural Networks (GNNs) can effectively capture both the topology and attribute information of a graph, have been extensively studied in many domains. Recently, there is an emerging trend that equips GNNs with knowledge distillation for better efficiency or effectiveness. However, to best our knowledge, existing methods applied on all employed predefined processes, which are controlled by several hyper-parameters without any supervision from performance distilled models. Such isolation...