Meta-Learning Based Knowledge Extrapolation for Knowledge Graphs in the Federated Setting
This addresses the challenge of adapting knowledge graph embeddings to new data in federated environments, which is incremental as it builds on existing meta-learning and KG methods.
The paper tackles the problem of embedding new entities and relations in emerging knowledge graphs within a federated setting, using meta-learning to train a graph neural network that constructs features for unseen components, and shows it outperforms inductive KG models and conventional embedding baselines.
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.