02/02/2021

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

Boris N. Oreshkin, Dmitri Carpov, Nicolas Chapados, Yoshua Bengio

Keywords:

Abstract Paper Similar Papers

Abstract: 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.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38949250
(Link will open in new window)
 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at AAAI 2021 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers

 0
 0
 0
 0
 5:18 
 0
 0
 0
 0
 11:00 
 0
 0
 0
 0
 5:07 
 0
 0
 0
 0
 3:22 
 0
 0
 0
 0
 4:59 
 0
 0
 0
 0
 3:54 
 0
 0
 0
 0
 15:04 
 0
 0
 0
 0
 12:41 
 0
 0
 0
 0
 10:52 
 0
 0
 0
 0
 5:54 
 0
 0
 0
 0
 15:01 
 0
 0
 0
 0
 5:10 
 0
 0
 0
 0
 3:12 
 1
 0
 0
 1
 12:23 
 0
 0
 0
 0
 14:52 
 0
 0
 0
 0
 15:00 
 0
 0
 0
 0
 5:12 
 0
 0
 0
 0
 15:13 
 0
 0
 0
 0
 14:49 
 0
 1
 0
 0
 5:08 
 0
 0
 0
 0
 5:07 
 0
 0
 0
 0
 14:56 
 0
 0
 0
 0
 11:11 
 0
 0
 0
 0
 5:00 
 0
 0
 0
 0
 15:05 
 0
 0
 0
 0
 9:58 
 0
 0
 0
 0
 12:36 
 0
 0
 0
 0
 3:17 
 0
 0
 0
 0
 12:51 
 0
 0
 0
 0
 5:25 
 0
 0
 0
 0
 14:26 
 0
 0
 0
 0
 14:05 
 0
 0
 0
 0
 5:19 
 0
 0
 0
 0
 3:23 
 0
 0
 0
 0
 7:36 
 0
 0
 0
 0
 7:10 
 0
 0
 0
 0
 14:00 
 0
 0
 0
 0
 5:07 
 0
 0
 0
 0
 17:12 
 0
 0
 0
 0
 15:02