# Efficient data augmentation using graph imputation neural networks

arXiv: https://arxiv.org/abs/1906.08502 · HTML: https://mlsanity.com/paper/1906.08502/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jun 2019.

## Built on by (most cited first, 2 of 2)

- [Data Augmentation for Graph Convolutional Network on Semi-Supervised Classification](https://mlsanity.com/paper/2106.08848/) (2021)
- [Graph Neural Networks: a bibliometrics overview](https://mlsanity.com/paper/2201.01188/) (2022)

## Abstract (arXiv)

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.