Back

Analysis and Augmentation of Small Datasets with Unsupervised Machine Learning

Dolgikh, S.

2021-04-25 health informatics
10.1101/2021.04.21.21254796 medRxiv
Show abstract

Analysis of small datasets presents a number of essential challenges not in the least due to insufficient sampling of characteristic patterns in the data making confident conclusions about the unknown distribution elusive and resulting in lower statistical confidence and higher error. In this work, a novel approach to augmentation of small datasets is proposed based on an ensemble of neural network models of unsupervised generative self-learning. Applying generative learning with an ensemble of individual models allowed to identify stable clusters of data points in the latent representations of the observable data. Several techniques of augmentation based on identified latent cluster structure were applied to produce new data points and enhance the dataset. The proposed method can be used with small and extremely small datasets to identify characteristics patterns, augment data and in some cases, improve accuracy of classification in the scenarios with strong deficit of labels.

Matching journals

The top 9 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.