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.
翻译:我们为空间回归建议了一个微小的学习方法。 虽然高斯进程(GPs)已被成功用于空间回归, 但它们在目标任务中需要许多观测才能达到高预测性能。 我们的模型是使用不同区域不同属性的空间数据集进行培训的, 并且根据一些观测的数据预测了未见区域的不可见属性值。 用我们的模型, 任务代表来自使用神经网络的给定小数据。 然后, 由带有GP框架的神经网络预测空间值, 其中任务特性由任务表达方式控制。 GP框架允许我们通过分析获得适应小数据的预测。 通过在目标函数中使用经调整的预测, 我们可以高效率和有成效地培训我们的模型, 以便测试性能在适应新给定的小数据时得到改善。 我们的实验显示, 拟议的方法比使用空间数据集的现有元学习方法更能实现预测性能。