UAI 2021poster3 citations

Learning to learn with Gaussian processes

Quoc Phong Nguyen, Bryan Kian Hsiang Low, Patrick Jaillet

Abstract

This paper presents Gaussian process meta-learning (GPML) for few-shot regression, which explicitly exploits the distance between regression problems/tasks using a novel task kernel. It contrasts sharply with the popular metric-based meta-learning approach which is based on the distance between data inputs or their embeddings in the few-shot learning literature. Apart from the superior predictive performance by capturing the diversity of different tasks, GPML offers a set of representative tasks that are useful for understanding the task distribution. We empirically demonstrate the performance and interpretability of GPML in several few-shot regression problems involving a multimodal task distribution and real-world datasets.

BibTeX
@InProceedings{pmlr-v161-nguyen21c,
  title = 	 {Learning to learn with Gaussian processes},
  author =       {Nguyen, Quoc Phong and Low, Bryan Kian Hsiang and Jaillet, Patrick},
  booktitle = 	 {Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence},
  pages = 	 {1466--1475},
  year = 	 {2021},
  editor = 	 {de Campos, Cassio and Maathuis, Marloes H.},
  volume = 	 {161},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {27--30 Jul},
  publisher =    {PMLR},
  pdf = 	 {https://proceedings.mlr.press/v161/nguyen21c/nguyen21c.pdf},
  url = 	 {https://proceedings.mlr.press/v161/nguyen21c.html},
  abstract = 	 {This paper presents Gaussian process meta-learning (GPML) for few-shot regression, which explicitly exploits the distance between regression problems/tasks using a novel task kernel. It contrasts sharply with the popular metric-based meta-learning approach which is based on the distance between data inputs or their embeddings in the few-shot learning literature. Apart from the superior predictive performance by capturing the diversity of different tasks, GPML offers a set of representative tasks that are useful for understanding the task distribution. We empirically demonstrate the performance and interpretability of GPML in several few-shot regression problems involving a multimodal task distribution and real-world datasets.}
}