Multimodal Meta-Learning for Time Series Regression

TL;DR

This paper introduces a multimodal meta-learning approach for time series regression that enables quick adaptation to new short-length time series by leveraging global information, outperforming baseline models in most experiments.

Contribution

It proposes a novel multimodal meta-learning method based on MAML, conditioning model parameters with an auxiliary network to encode global time series features.

Findings

Outperforms baselines in 9 of 12 experiments

Enables fast learning from few data points

Effective across diverse domains like pollution, heart-rate, and battery data

Abstract

Recent work has shown the efficiency of deep learning models such as Fully Convolutional Networks (FCN) or Recurrent Neural Networks (RNN) to deal with Time Series Regression (TSR) problems. These models sometimes need a lot of data to be able to generalize, yet the time series are sometimes not long enough to be able to learn patterns. Therefore, it is important to make use of information across time series to improve learning. In this paper, we will explore the idea of using meta-learning for quickly adapting model parameters to new short-history time series by modifying the original idea of Model Agnostic Meta-Learning (MAML) \cite{finn2017model}. Moreover, based on prior work on multimodal MAML \cite{vuorio2019multimodal}, we propose a method for conditioning parameters of the model through an auxiliary network that encodes global information of the time series to extract meta-features. Finally, we apply the data to time series of different domains, such as pollution measurements, heart-rate sensors, and electrical battery data. We show empirically that our proposed meta-learning method learns TSR with few data fast and outperforms the baselines in 9 of 12 experiments.