Graph imputation neural networks augment semi-supervised datasets up to 10x by reconstructing heavily damaged samples on a similarity graph, improving over fully-supervised baselines on benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Efficient data augmentation using graph imputation neural networks
Graph imputation neural networks augment semi-supervised datasets up to 10x by reconstructing heavily damaged samples on a similarity graph, improving over fully-supervised baselines on benchmarks.