返回
Rule learning with causal intervention for knowledge graph reasoning
DOI:10.1016/j.asoc.2026.114802.png)
摘要
En 中文
• 显式地在整体规则学习框架中采用因果干预进行知识图谱推理;
• 模型化因果性和混淆因素,并恢复它们之间的连接以模拟因果干预;
• 将因果关系与混淆因素解耦以获取更高质量的规则;
• 通过在五个公开可用数据集上进行实验来展示该框架的性能。
Keyword:
causal intervention
knowledge graph reasoning
rule learning
confounders
holistic framework
期刊
IF:
6.6
论文数:
1.4W
被引数:
4.8W
机构
暂无机构信息
引用论文
Capsule neural tensor networks with multi-aspect information for Few-shot Knowledge Graph Completion具有多方面信息的胶囊神经张量网络用于少镜头知识图补全
NEURAL NETWORKS
IF6.3
CODEX: COunterfactual Deep learning for the in silico EXploration of cancer cell line perturbationsCODEX:用于癌症细胞系扰动在体模拟的反事实深度学习
DensE: An enhanced non-commutative representation for knowledge graph embedding with adaptive semantic hierarchy
NEUROCOMPUTING
IF6.5

