Semi-Supervised Learning by Label Gradient Alignment Article Swipe

PDF

Related Concepts

Gradient descent Artificial intelligence Metric (unit) Computer science Pattern recognition (psychology) Point (geometry) Metric space Space (punctuation) Semi-supervised learning Supervised learning Machine learning Mathematics Artificial neural network Operating system Mathematical analysis Economics Geometry Operations management

Jacob Jackson , John Schulman ·

YOU? · · 2019 · Open Access · · DOI: https://doi.org/10.48550/arxiv.1902.02336 · OA: W2911603976

We present label gradient alignment, a novel algorithm for semi-supervised learning which imputes labels for the unlabeled data and trains on the imputed labels. We define a semantically meaningful distance metric on the input space by mapping a point (x, y) to the gradient of the model at (x, y). We then formulate an optimization problem whose objective is to minimize the distance between the labeled and the unlabeled data in this space, and we solve it by gradient descent on the imputed labels. We evaluate label gradient alignment using the standardized architecture introduced by Oliver et al. (2018) and demonstrate state-of-the-art accuracy in semi-supervised CIFAR-10 classification.