返回
A multi-hop Shapley-based framework for graph convolutional network node classification explanation
DOI:10.1016/j.asoc.2025.113615.png)
摘要
En 中文
• 提出一种计算图构建方法以整合多跳边。
• 引入一种采样策略以在不同规模下采样联盟。
• 通过关键边提高GCN对正确类别预测的置信度。
Keyword:
computational graph
multi-hop edges
sampling strategy
coalition sampling
GCN confidence
期刊
IF:
6.6
论文数:
1.4W
被引数:
4.8W
机构
引用论文
On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation通过逐层相关性传播对非线性分类器决策的逐像素解释
PLOS ONE
IF0
Cross-graph Interaction NetworksGuo, Q.; Yang, X.; Ding, W.; Qian, Y. Cross-Graph Interaction Networks. IEEE Trans. Knowl. Data Eng. 2025, 37, 2341–2355. [Google Scholar] [CrossRef]
Fuzzy feature factorization machine: Bridging feature interaction, selection, and construction模糊特征分解机: 桥接特征交互,选择和构造
Stochastic jump diffusion process informed neural networks for accurate American option pricing under data scarcity基于随机跳跃扩散过程的神经网络在数据稀缺条件下的美式期权定价

