Few-shot Learning for Spatial Regression

10/09/2020
by   Tomoharu Iwata, et al.
0

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.

READ FULL TEXT

page 2

page 7

research
03/01/2021

Meta-learning One-class Classifiers with Eigenvalue Solvers for Supervised Anomaly Detection

Neural network-based anomaly detection methods have shown to achieve hig...
research
10/18/2022

Few-Shot Learning of Compact Models via Task-Specific Meta Distillation

We consider a new problem of few-shot learning of compact models. Meta-l...
research
11/01/2021

End-to-End Learning of Deep Kernel Acquisition Functions for Bayesian Optimization

For Bayesian optimization (BO) on high-dimensional data with complex str...
research
03/01/2021

Meta-learning representations for clustering with infinite Gaussian mixture models

For better clustering performance, appropriate representations are criti...
research
04/19/2021

Few-shot Learning for Topic Modeling

Topic models have been successfully used for analyzing text documents. H...
research
11/18/2022

Active Learning with Convolutional Gaussian Neural Processes for Environmental Sensor Placement

Deploying environmental measurement stations can be a costly and time-co...
research
10/06/2021

Probabilistic Metamodels for an Efficient Characterization of Complex Driving Scenarios

To systematically validate the safe behavior of automated vehicles (AV),...

Please sign up or login with your details

Forgot password? Click here to reset