A5020113235- Advanced Graph Neural Networks
- Recommender Systems and Techniques
- Domain Adaptation and Few-Shot Learning
- Topic Modeling
- Advanced Neural Network Applications
By jointly modeling user-item interactions and knowledge graph (KG) information, KG-based recommender systems have shown their superiority in alleviating data sparsity cold start problems. Recently, neural networks (GNNs) been widely used recommendation, owing to the strong ability of capturing high-order structural information. However, we argue that existing GNN-based methods following two limitations. Interaction domination: supervision signal interaction will dominate model training,...
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...