Efficient data augmentation using graph imputation neural networks
This addresses the problem of limited labeled data in semi-supervised learning, but it is incremental as it builds on an existing GINN framework.
The paper tackles data augmentation in semi-supervised learning by using a graph imputation neural network (GINN) to reconstruct damaged nodes, achieving up to 10x dataset augmentation and significant improvements over fully-supervised models on benchmark datasets.
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.