# Invariant Representations from Adversarially Censored Autoencoders

arXiv: https://arxiv.org/abs/1805.08097 · HTML: https://mlsanity.com/paper/1805.08097/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 May 2018.

## Built on by (most cited first, 3 of 3)

- [AutoTransfer: Subject Transfer Learning with Censored Representations on Biosignals Data](https://mlsanity.com/paper/2112.09796/) (2021)
- [quEEGNet: Quantum AI for Biosignal Processing](https://mlsanity.com/paper/2210.00864/) (2022)
- [Stabilizing Subject Transfer in EEG Classification with Divergence Estimation](https://mlsanity.com/paper/2310.08762/) (2023)

## Abstract (arXiv)

We combine conditional variational autoencoders (VAE) with adversarial censoring in order to learn invariant representations that are disentangled from nuisance/sensitive variations. In this method, an adversarial network attempts to recover the nuisance variable from the representation, which the VAE is trained to prevent. Conditioning the decoder on the nuisance variable enables clean separation of the representation, since they are recombined for model learning and data reconstruction. We show this natural approach is theoretically well-founded with information-theoretic arguments. Experiments demonstrate that this method achieves invariance while preserving model learning performance, and results in visually improved performance for style transfer and generative sampling tasks.