ServiceNow Research

Meta-Learning Framework with Applications to Zero-Shot Time Series Forecasting


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 this using a broad meta-learning framework which we show subsumes many existing meta-learning algorithms. Our theoretical analysis suggests that residual connections act as a meta-learning adaptation mechanism, generating a subset of task-specific parameters based on a given TS input, thus gradually expanding the expressive power of the architecture on-the-fly. The same mechanism is shown via linearization analysis to have the interpretation of a sequential update of the final linear layer. Our empirical results on a wide range of data emphasize the importance of the identified meta-learning mechanisms for successful zero-shot univariate forecasting, suggesting 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.

International Conference on Learning Representations (ICLR)
Nicolas Chapados
Nicolas Chapados
VP of Research

VP of Research at Research Management located at Montreal, QC, Canada.

Yoshua Bengio
Yoshua Bengio
Research Advisor

Research Advisor at Human Decision Support located at Montreal, QC, Canada.