Seminar LIGM - An Adversarial Regularization for Semi-Supervised Training of Structured Output Neural Networks

A seminar of the A3SI team of the LIGM (joint research unit of the University Paris Est) will take place on Wednesday 26 April at 13.45 in the B 412 meeting room of the IMAGINE group (ENPC - Bat Coriolis).

An Adversarial Regularization for Semi-Supervised Training of Structured Output Neural Networks
Mateusz Kozinski
GREYC, Université de Caen

Abstract: My talk is is going to be focused on semi-supervised training of structured-output neural networks. The problem is of broad interest, because training deep neural networks requires large amounts of annotated data, and producing structured annotations is costly. On the other hand, unannotated input data is often cheap to acquire. I will show that this unannotated data can be used for training structured-output models in a semi-supervised scenario. The idea is inspired by the Generative Adversarial Networks, and consists in generating an error signal for the unlabelled data by means of a discriminator neural network. To be source of a useful error signal, the discriminator needs to capture quality of the structured output. This can be achieved by training the discriminator to differentiate between structured outputs obtained for the labelled training data (qualitatively better) and the outputs obtained for unlabelled data, not used for training (qualitatively worse). Initial experiments suggest that this approach may lead to decreasing the volume of labels required to attain a given precision by a significant factor.