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

Abstract

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.

icml2020

References in corpus (7)

• Prototypical Networks for Few-shot Learning
• A Simple Neural Attentive Meta-Learner
• RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
• Few-Shot Learning with Graph Neural Networks
• GMNN: Graph Markov Neural Networks
• FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation
• Meta-Learning for Stochastic Gradient MCMC

Cited by in corpus (8)

• A Survey on Knowledge Graphs: Representation, Acquisition and Applications
• A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
• Speaker-Oriented Latent Structures for Dialogue-Based Relation Extraction
• Entity Concept-enhanced Few-shot Relation Extraction
• SocAoG: Incremental Graph Parsing for Social Relation Inference in Dialogues
• What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Data
• Uncovering Main Causalities for Long-tailed Information Extraction
• Ensemble Making Few-Shot Learning Stronger