# Multimodal Meta-Learning for Time Series Regression

arXiv: https://arxiv.org/abs/2108.02842 · HTML: https://mlsanity.com/paper/2108.02842/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 23 references that are in the map.
- First posted on arXiv 5 Aug 2021.

## Builds on (most cited first, 13 of 13)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [N-BEATS: Neural basis expansion analysis for interpretable time series forecasting](https://mlsanity.com/paper/1905.10437/) (2019)
- [TADAM: Task dependent adaptive metric for improved few-shot learning](https://mlsanity.com/paper/1805.10123/) (2018)
- [A Recurrent Latent Variable Model for Sequential Data](https://mlsanity.com/paper/1506.02216/) (2015)
- [Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulation](https://mlsanity.com/paper/1910.13616/) (2019)
- [Meta-learning framework with applications to zero-shot time-series forecasting](https://mlsanity.com/paper/2002.02887/) (2020)
- [Meta-Learning Requires Meta-Augmentation](https://mlsanity.com/paper/2007.05549/) (2020)
- [Variational Recurrent Auto-Encoders](https://mlsanity.com/paper/1412.6581/) (2014)
- [Meta-Learning for Few-Shot Time Series Classification](https://mlsanity.com/paper/1909.07155/) (2019)
- [Few-shot Learning for Time-series Forecasting](https://mlsanity.com/paper/2009.14379/) (2020)

## Built on by (most cited first, 7 of 7)

- [Few-Shot Forecasting of Time-Series with Heterogeneous Channels](https://mlsanity.com/paper/2204.03456/) (2022)
- [Task Aware Modulation using Representation Learning: An Approach for Few Shot Learning in Environmental Systems](https://mlsanity.com/paper/2310.04727/) (2023)
- [Two-Timescale Stochastic Approximation for Bilevel Optimisation Problems in Continuous-Time Models](https://mlsanity.com/paper/2206.06995/) (2022)
- [A behavioural transformer for effective collaboration between a robot and a non-stationary human](https://mlsanity.com/paper/2307.13447/) (2023)
- [Forecasting Early with Meta Learning](https://mlsanity.com/paper/2307.09796/) (2023)
- [Successive Model-Agnostic Meta-Learning for Few-Shot Fault Time Series Prognosis](https://mlsanity.com/paper/2311.02300/) (2023)
- [TMAML: Temporal Model-Agnostic Meta-Learning for Cold-Start Time Series Forecasting](https://mlsanity.com/paper/2610.04547/) (2026)

## Abstract (arXiv)

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) citefinn2017model. Moreover, based on prior work on multimodal MAML citevuorio2019multimodal, 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.