English

On Adversarial Mixup Resynthesis

Machine Learning 2019-10-25 v4 Machine Learning

Abstract

In this paper, we explore new approaches to combining information encoded within the learned representations of auto-encoders. We explore models that are capable of combining the attributes of multiple inputs such that a resynthesised output is trained to fool an adversarial discriminator for real versus synthesised data. Furthermore, we explore the use of such an architecture in the context of semi-supervised learning, where we learn a mixing function whose objective is to produce interpolations of hidden states, or masked combinations of latent representations that are consistent with a conditioned class label. We show quantitative and qualitative evidence that such a formulation is an interesting avenue of research.

Keywords

Cite

@article{arxiv.1903.02709,
  title  = {On Adversarial Mixup Resynthesis},
  author = {Christopher Beckham and Sina Honari and Vikas Verma and Alex Lamb and Farnoosh Ghadiri and R Devon Hjelm and Yoshua Bengio and Christopher Pal},
  journal= {arXiv preprint arXiv:1903.02709},
  year   = {2019}
}

Comments

'Camera-ready draft'

R2 v1 2026-06-23T08:00:39.039Z