.png){kind=icon}
返回
Lifelong knowledge graph embedding via diffusion model
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neunet.2026.108630.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
• We proposed a unified perspective of embedding space drift for lifelong knowledge graph embedding. • We designed a diffusion-based knowledge graph embedding framework for the lifelong setting. • Our framework avoids catastrophic forgetting and enables efficient learning of new entities. • Our framework achieves improvements in different incremental scenarios.
期刊
IF:
6.3
论文数:
8.2K
被引数:
3.0W
机构
引用论文
GUIDE: Training Deep Graph Neural Networks via Guided Dropout Over Edges指南: 通过引导边缘上的Dropout训练深度图神经网络
PREAI
分享收藏FEDGKD: Toward Heterogeneous Federated Learning via Global Knowledge DistillationFEDGKD: 通过全球知识蒸馏实现异构联邦学习
PREAI
分享收藏LollipopE: Bi-centered lollipop embedding for complex logic query on knowledge graph.png)
NEURAL NETWORKS
NEURAL NETWORKSIF6.3
PREAI
分享收藏
没有更多内容
没有更多内容