Research Area:  Machine Learning

Abstract:

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.

Keywords:  
Knowledge graphs
Federated setting
Meta-learning
Graph neural network
Embedding methods

Author(s) Name:  Mingyang Chen, Wen Zhang, Zhen Yao, Xiangnan Chen, Mengxiao Ding, Fei Huang, Huajun Chen

Publisher name:  arXiv.2205.04692

DOI:  10.48550/arXiv.2205.04692

Volume Information:  

Paper Link:   https://arxiv.org/abs/2205.04692