Skip to yearly menu bar Skip to main content


Few-shot Relation Extraction via Bayesian Meta-learning on Relation Graphs

Meng Qu · Tianyu Gao · Louis-Pascal Xhonneux · Jian Tang

Keywords: [ Bayesian Deep Learning ] [ Networks and Relational Learning ] [ Meta-learning and Automated ML ] [ Natural Language Processing / Dialogue ] [ Applications - Language, Speech and Dialog ]


This paper studies few-shot relation extraction, which aims at predicting the relation for a pair of entities in a sentence by training with a few labeled examples in each relation. To more effectively generalize to new relations, in this paper we study the relationships between different relations and propose to leverage a global relation graph. We propose a novel Bayesian meta-learning approach to effectively learn the posterior distribution of the prototype vectors of relations, where the initial prior of the prototype vectors is parameterized with a graph neural network on the global relation graph. Moreover, to effectively optimize the posterior distribution of the prototype vectors, we propose to use the stochastic gradient Langevin dynamics, which is related to the MAML algorithm but is able to handle the uncertainty of the prototype vectors. The whole framework can be effectively and efficiently optimized in an end-to-end fashion. Experiments on two benchmark datasets prove the effectiveness of our proposed approach against competitive baselines in both the few-shot and zero-shot settings.

Chat is not available.