.png){kind=icon}
返回
Inductive relation prediction with information bottleneck
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2024.128503.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Inductive relation prediction is an important learning task for knowledge graph completion that aims to infer new facts from existing ones. Previous works that focus on path-based are naturally limited in expressive. The methods based on graph neural network framework consider all paths thus improving the performance. However, fusing all paths information may extract features that are spuriously correlated with the prediction. By analogy to the human reasoning process, we observe that only a small subset of the critical paths determine the prediction. In this work, we propose a novel framework that extracts such critical paths to make inductive relation prediction on K nowledge G raph with G raph I nformation B ottleneck (KG KG-GIB). ). KG-GIB is the first attempt to advance the Graph Information Bottleneck (GIB) for inductive relation prediction. Derived from the GIB principle, KG-GIB extracts critical paths which preserves task-relevant paths and blocks information from task-irrelevant paths. The extracted critical paths are expected to be more generalizable and interpretable. Extensive experiments on both synthetic and real-world datasets demonstrate the effectiveness of KG-GIB.
Keyword:
Inductive relation prediction
Knowledge graph completion
Knowledge graph
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
引用论文
CARM: Confidence-aware recommender model via review representation learning and historical rating behavior in the online platforms.png)
NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏Recalibration convolutional networks for learning interaction knowledge graph embeddingNEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏Learning Knowledge Graph Embedding With Heterogeneous Relation Attention Networks基于异质关系注意网络的学习知识图谱嵌入
PREAI
分享收藏
查看更多内容