Meta-Learning with Shared Amortized Variational Inference - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2020

Meta-Learning with Shared Amortized Variational Inference


We propose a novel amortized variational inference scheme for an empirical Bayes meta-learning model, where model parameters are treated as latent variables. We learn the prior distribution over model parameters conditioned on limited training data using a variational autoencoder approach. Our framework proposes sharing the same amor-tized inference network between the conditional prior and variational posterior distributions over the model parameters. While the posterior leverages both the labeled support and query data, the conditional prior is based only on the labeled support data. We show that in earlier work, relying on Monte-Carlo approximation, the conditional prior collapses to a Dirac delta function. In contrast, our variational approach prevents this collapse and preserves uncertainty over the model parameters. We evaluate our approach on the miniImageNet, CIFAR-FS and FC100 datasets, and present results demonstrating its advantages over previous work.
Fichier principal
Vignette du fichier
main.pdf (6.71 Mo) Télécharger le fichier
samovar.pdf (61.21 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-02925830 , version 1 (31-08-2020)



Ekaterina Iakovleva, Jakob Verbeek, Karteek Alahari. Meta-Learning with Shared Amortized Variational Inference. ICML 2020 - 37th International Conference on Machine Learning, Jul 2020, Vienna (Online), Austria. pp.4572-4582. ⟨hal-02925830⟩
184 View
206 Download



Gmail Mastodon Facebook X LinkedIn More