Few-shot Learning for Spatial Regression

Abstract

We propose a few-shot learning method for spatial regression. Although Gaussian processes (GPs) have been successfully used for spatial regression, they require many observations in the target task to achieve a high predictive performance. Our model is trained using spatial datasets on various attributes in various regions, and predicts values on unseen attributes in unseen regions given a few observed data. With our model, a task representation is inferred from given small data using a neural network. Then, spatial values are predicted by neural networks with a GP framework, in which task-specific properties are controlled by the task representations. The GP framework allows us to analytically obtain predictions that are adapted to small data. By using the adapted predictions in the objective function, we can train our model efficiently and effectively so that the test predictive performance improves when adapted to newly given small data. In our experiments, we demonstrate that the proposed method achieves better predictive performance than existing meta-learning methods using spatial datasets.

References in corpus (15)

• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Prototypical Networks for Few-shot Learning
• Meta-SGD: Learning to Learn Quickly for Few-Shot Learning
• Towards a Neural Statistician
• Hierarchically Structured Meta-learning
• Estimation in semiparametric spatial regression
• Stochastic Variational Deep Kernel Learning
• Generalized Inner Loop Meta-Learning
• One-Shot Generalization in Deep Generative Models
• Few-shot Autoregressive Density Estimation: Towards Learning to Learn Distributions
• Improving Output Uncertainty Estimation and Generalization in Deep Learning via Neural Network Gaussian Processes
• The Variational Homoencoder: Learning to learn high capacity generative models from few examples
• Meta-Learning Mean Functions for Gaussian Processes
• Adaptive Deep Kernel Learning
• Efficient Transfer Bayesian Optimization with Auxiliary Information

Cited by in corpus (2)

• End-to-End Learning of Deep Kernel Acquisition Functions for Bayesian Optimization
• Meta-learning for Matrix Factorization without Shared Rows or Columns