English

Efficient data augmentation using graph imputation neural networks

Machine Learning 2019-06-21 v1 Machine Learning

Abstract

Recently, data augmentation in the semi-supervised regime, where unlabeled data vastly outnumbers labeled data, has received a considerable attention. In this paper, we describe an efficient technique for this task, exploiting a recent framework we proposed for missing data imputation called graph imputation neural network (GINN). The key idea is to leverage both supervised and unsupervised data to build a graph of similarities between points in the dataset. Then, we augment the dataset by severely damaging a few of the nodes (up to 80\% of their features), and reconstructing them using a variation of GINN. On several benchmark datasets, we show that our method can obtain significant improvements compared to a fully-supervised model, and we are able to augment the datasets up to a factor of 10x. This points to the power of graph-based neural networks to represent structural affinities in the samples for tasks of data reconstruction and augmentation.

Keywords

Cite

@article{arxiv.1906.08502,
  title  = {Efficient data augmentation using graph imputation neural networks},
  author = {Indro Spinelli and Simone Scardapane and Michele Scarpiniti and Aurelio Uncini},
  journal= {arXiv preprint arXiv:1906.08502},
  year   = {2019}
}

Comments

Presented at the 2019 Italian Workshop on Neural Networks (WIRN'19)

R2 v1 2026-06-23T09:58:46.714Z