Meta-learning framework with applications to zero-shot time-series forecasting
This addresses the challenge of deploying forecasting models across different datasets without retraining, though it appears incremental as it builds on existing meta-learning algorithms.
The paper tackles the problem of zero-shot time-series forecasting by proposing a meta-learning framework that trains on diverse source datasets and generalizes to new target datasets without retraining, achieving performance at least as good as state-of-practice models.
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.