Related papers: Uncertainty-Aware Meta-Learning for Multimodal Task Distributions

Uncertainty-Aware Meta-Learning for Multimodal Task Distributions

URL: http://arxiv.org/abs/2210.01881v1
Date: Tue, 4 Oct 2022 20:02:25 GMT
Title: Uncertainty-Aware Meta-Learning for Multimodal Task Distributions
Authors: Cesar Almecija, Apoorva Sharma and Navid Azizan
Abstract summary: We present UnLiMiTD (uncertainty-aware meta-learning for multimodal task distributions) We take a probabilistic perspective and train a parametric, tuneable distribution over tasks on the meta-dataset. We demonstrate that UnLiMiTD's predictions compare favorably to, and outperform in most cases, the standard baselines.
Score: 3.7470451129384825
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Meta-learning or learning to learn is a popular approach for learning new tasks with limited data (i.e., few-shot learning) by leveraging the commonalities among different tasks. However, meta-learned models can perform poorly when context data is limited, or when data is drawn from an out-of-distribution (OoD) task. Especially in safety-critical settings, this necessitates an uncertainty-aware approach to meta-learning. In addition, the often multimodal nature of task distributions can pose unique challenges to meta-learning methods. In this work, we present UnLiMiTD (uncertainty-aware meta-learning for multimodal task distributions), a novel method for meta-learning that (1) makes probabilistic predictions on in-distribution tasks efficiently, (2) is capable of detecting OoD context data at test time, and (3) performs on heterogeneous, multimodal task distributions. To achieve this goal, we take a probabilistic perspective and train a parametric, tuneable distribution over tasks on the meta-dataset. We construct this distribution by performing Bayesian inference on a linearized neural network, leveraging Gaussian process theory. We demonstrate that UnLiMiTD's predictions compare favorably to, and outperform in most cases, the standard baselines, especially in the low-data regime. Furthermore, we show that UnLiMiTD is effective in detecting data from OoD tasks. Finally, we confirm that both of these findings continue to hold in the multimodal task-distribution setting.