Nature vs. Nurture: Feature vs. Structure for Graph Neural Networks
Pattern Recognition Letters(2022)
摘要
•Node features and graph structure have impacts to the performance of GNN models.•Graphs can be constructed by connecting node features via a latent function.•GNNs can be used to reconstruct node features from graph structure.•New graph structures can be created by node features with better predictability.•The characteristics of a GNN model can be transferred to unseen graphs.
更多查看译文
关键词
graph neural networks,transferability
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要