联邦环境下基于元学习的知识图谱知识外推
Meta-Learning Based Knowledge Extrapolation for Knowledge Graphs in the Federated Setting
摘要:
我们研究了知识外推问题,以嵌入新的组件(即,实体和关系),这些实体和关系伴随着联邦设置中的新兴知识图谱(KG)而出现。在这个问题中,在现有KG上训练的模型需要嵌入一个新的KG,其中包含看不见的实体和关系。为了解决这个问题,我们引入了元学习设置,在现有KG上采样一组任务,以模仿新兴KG上的链接预测任务。基于采样任务,我们元训练一个图神经网络框架,该框架可以基于结构信息为看不见的组件构建特征,并输出嵌入。实验结果表明,我们提出的方法可以有效地嵌入看不见的组件,并优于模型,考虑电感设置的KG和基线,直接使用传统的KG嵌入方法。
英文摘要:
We study the knowledge extrapolation problem to embed new components (i.e., entities and relations) that come with emerging knowledge graphs (KGs) in the federated setting. In this problem, a model trained on an existing KG needs to embed an emerging KG with unseen entities and relations. To solve this problem, we introduce the meta-learning setting, where a set of tasks are sampled on the existing KG to mimic the link prediction task on the emerging KG. Based on sampled tasks, we meta-train a graph neural network framework that can construct features for unseen components based on structural information and output embeddings for them. Experimental results show that our proposed method can effectively embed unseen components and outperforms models that consider inductive settings for KGs and baselines that directly use conventional KG embedding methods.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。