Semi-supervised Learning with GANs: Manifold Invariance with Improved Inference
This work addresses semi-supervised learning challenges for machine learning practitioners, offering incremental improvements over existing GAN-based methods.
The paper tackles the problem of semi-supervised learning with limited labeled data by using GANs to estimate the data manifold's tangent space and inject invariances into the classifier, resulting in considerable empirical gains over baselines, especially when labeled examples are few.
Semi-supervised learning methods using Generative Adversarial Networks (GANs) have shown promising empirical success recently. Most of these methods use a shared discriminator/classifier which discriminates real examples from fake while also predicting the class label. Motivated by the ability of the GANs generator to capture the data manifold well, we propose to estimate the tangent space to the data manifold using GANs and employ it to inject invariances into the classifier. In the process, we propose enhancements over existing methods for learning the inverse mapping (i.e., the encoder) which greatly improves in terms of semantic similarity of the reconstructed sample with the input sample. We observe considerable empirical gains in semi-supervised learning over baselines, particularly in the cases when the number of labeled examples is low. We also provide insights into how fake examples influence the semi-supervised learning procedure.