Meta-learning framework with applications to zero-shot time-series forecasting

02/07/2020
by   Boris N. Oreshkin, et al.
63

Can meta-learning discover generic ways of processing time-series (TS) from a diverse dataset so as to greatly improve generalization on new TS coming from different datasets? This work provides positive evidence to demonstrate this using a broad meta-learning framework which we show subsumes many existing meta-learning algorithms as specific cases. We further identify via theoretical analysis the meta-learning adaptation mechanisms within N-BEATS, a recent neural TS forecasting model. Our meta-learning theory predicts that N-BEATS iteratively generates a subset of its task-specific parameters based on a given TS input, thus gradually expanding the expressive power of the architecture on-the-fly. Our empirical results emphasize the importance of meta-learning for successful zero-shot forecasting to new sources of TS, supporting the claim that it is viable to train a neural network on a source TS dataset and deploy it on a different target TS dataset without retraining, resulting in performance that is at least as good as that of state-of-practice univariate forecasting models.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/20/2022

Boosting Natural Language Generation from Instructions with Meta-Learning

Recent work has shown that language models (LMs) trained with multi-task...
research
07/19/2023

Forecasting Early with Meta Learning

In the early observation period of a time series, there might be only a ...
research
02/04/2023

Cross-Frequency Time Series Meta-Forecasting

Meta-forecasting is a newly emerging field which combines meta-learning ...
research
10/22/2020

Meta-Learning for Domain Generalization in Semantic Parsing

The importance of building semantic parsers which can be applied to new ...
research
05/12/2023

Meta-Optimization for Higher Model Generalizability in Single-Image Depth Prediction

Model generalizability to unseen datasets, concerned with in-the-wild ro...
research
08/05/2021

Multimodal Meta-Learning for Time Series Regression

Recent work has shown the efficiency of deep learning models such as Ful...
research
06/04/2019

Neuromorphic Architecture Optimization for Task-Specific Dynamic Learning

The ability to learn and adapt in real time is a central feature of biol...

Please sign up or login with your details

Forgot password? Click here to reset