Learning a Universal Template for Few-shot Dataset Generalization

Eleni Triantafillou, Hugo Larochelle, Richard Zemel, Vincent Dumoulin
Proceedings of the 38th International Conference on Machine Learning, PMLR 139:10424-10433, 2021.

Abstract

Few-shot dataset generalization is a challenging variant of the well-studied few-shot classification problem where a diverse training set of several datasets is given, for the purpose of training an adaptable model that can then learn classes from \emph{new datasets} using only a few examples. To this end, we propose to utilize the diverse training set to construct a \emph{universal template}: a partial model that can define a wide array of dataset-specialized models, by plugging in appropriate components. For each new few-shot classification problem, our approach therefore only requires inferring a small number of parameters to insert into the universal template. We design a separate network that produces an initialization of those parameters for each given task, and we then fine-tune its proposed initialization via a few steps of gradient descent. Our approach is more parameter-efficient, scalable and adaptable compared to previous methods, and achieves the state-of-the-art on the challenging Meta-Dataset benchmark.

Cite this Paper

BibTeX
@InProceedings{pmlr-v139-triantafillou21a, title = {Learning a Universal Template for Few-shot Dataset Generalization}, author = {Triantafillou, Eleni and Larochelle, Hugo and Zemel, Richard and Dumoulin, Vincent}, booktitle = {Proceedings of the 38th International Conference on Machine Learning}, pages = {10424--10433}, year = {2021}, editor = {Meila, Marina and Zhang, Tong}, volume = {139}, series = {Proceedings of Machine Learning Research}, month = {18--24 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v139/triantafillou21a/triantafillou21a.pdf}, url = {https://proceedings.mlr.press/v139/triantafillou21a.html}, abstract = {Few-shot dataset generalization is a challenging variant of the well-studied few-shot classification problem where a diverse training set of several datasets is given, for the purpose of training an adaptable model that can then learn classes from \emph{new datasets} using only a few examples. To this end, we propose to utilize the diverse training set to construct a \emph{universal template}: a partial model that can define a wide array of dataset-specialized models, by plugging in appropriate components. For each new few-shot classification problem, our approach therefore only requires inferring a small number of parameters to insert into the universal template. We design a separate network that produces an initialization of those parameters for each given task, and we then fine-tune its proposed initialization via a few steps of gradient descent. Our approach is more parameter-efficient, scalable and adaptable compared to previous methods, and achieves the state-of-the-art on the challenging Meta-Dataset benchmark.} }
Endnote
%0 Conference Paper %T Learning a Universal Template for Few-shot Dataset Generalization %A Eleni Triantafillou %A Hugo Larochelle %A Richard Zemel %A Vincent Dumoulin %B Proceedings of the 38th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2021 %E Marina Meila %E Tong Zhang %F pmlr-v139-triantafillou21a %I PMLR %P 10424--10433 %U https://proceedings.mlr.press/v139/triantafillou21a.html %V 139 %X Few-shot dataset generalization is a challenging variant of the well-studied few-shot classification problem where a diverse training set of several datasets is given, for the purpose of training an adaptable model that can then learn classes from \emph{new datasets} using only a few examples. To this end, we propose to utilize the diverse training set to construct a \emph{universal template}: a partial model that can define a wide array of dataset-specialized models, by plugging in appropriate components. For each new few-shot classification problem, our approach therefore only requires inferring a small number of parameters to insert into the universal template. We design a separate network that produces an initialization of those parameters for each given task, and we then fine-tune its proposed initialization via a few steps of gradient descent. Our approach is more parameter-efficient, scalable and adaptable compared to previous methods, and achieves the state-of-the-art on the challenging Meta-Dataset benchmark.
APA
Triantafillou, E., Larochelle, H., Zemel, R. & Dumoulin, V.. (2021). Learning a Universal Template for Few-shot Dataset Generalization. Proceedings of the 38th International Conference on Machine Learning, in Proceedings of Machine Learning Research 139:10424-10433 Available from https://proceedings.mlr.press/v139/triantafillou21a.html.

Related Material