Few-shot Learning for Spatial Regression
This work addresses the challenge of spatial regression with few observations, which is incremental as it builds on existing meta-learning and GP approaches.
The paper tackles the problem of spatial regression with limited data by proposing a few-shot learning method that combines neural networks with a Gaussian process framework, achieving better predictive performance than existing meta-learning methods in experiments.
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.