Unsupervised Data Selection for Supervised Learning

10/29/2018

∙

Recent research put a big effort in the development of deep learning architectures and optimizers obtaining impressive results in areas ranging from vision to language processing. However little attention has been addressed to the need of a methodological process of data collection. In this work we show that high quality data for supervised learning can be selected in an unsupervised manner and that by doing so one can obtain models capable to generalize better than in the case of random training set construction.

READ FULL TEXT

Unsupervised Data Selection for Supervised Learning

Semi-Unsupervised Learning with Deep Generative Models: Clustering and Classifying using Ultra-Sparse Labels

Cold PAWS: Unsupervised class discovery and the cold-start problem

What Really is Deep Learning Doing?

Rethinking supervised learning: insights from biological learning and from calling it by its name

Evaluating and Crafting Datasets Effective for Deep Learning With Data Maps

CycleGT: Unsupervised Graph-to-Text and Text-to-Graph Generation via Cycle Training

Spectroscopic data de-noising via training-set-free deep learning method

Unsupervised Data Selection for Supervised Learning

Related Research

Semi-Unsupervised Learning with Deep Generative Models: Clustering and Classifying using Ultra-Sparse Labels

Cold PAWS: Unsupervised class discovery and the cold-start problem

What Really is Deep Learning Doing?

Rethinking supervised learning: insights from biological learning and from calling it by its name

Evaluating and Crafting Datasets Effective for Deep Learning With Data Maps

CycleGT: Unsupervised Graph-to-Text and Text-to-Graph Generation via Cycle Training

Spectroscopic data de-noising via training-set-free deep learning method