# Unsupervised Adversarial Invariance

arXiv: https://arxiv.org/abs/1809.10083 · HTML: https://mlsanity.com/paper/1809.10083/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Sep 2018.

## Built on by (most cited first, 14 of 14)

- [Factorizing Knowledge in Neural Networks](https://mlsanity.com/paper/2207.03337/) (2022)
- [Negative Data Augmentation](https://mlsanity.com/paper/2102.05113/) (2021)
- [A Survey on Wi-Fi Sensing Generalizability: Taxonomy, Techniques, Datasets, and Future Research Prospects](https://mlsanity.com/paper/2503.08008/) (2025)
- [Fair Representations by Compression](https://mlsanity.com/paper/2105.14044/) (2021)
- [Learning Invariant Representations using Inverse Contrastive Loss](https://mlsanity.com/paper/2102.08343/) (2021)
- [Set-to-Sequence Methods in Machine Learning: a Review](https://mlsanity.com/paper/2103.09656/) (2021)
- [Myope Models -- Are face presentation attack detection models short-sighted?](https://mlsanity.com/paper/2111.11127/) (2021)
- [Information-Theoretic Bias Assessment Of Learned Representations Of Pretrained Face Recognition](https://mlsanity.com/paper/2111.04673/) (2021)
- [Learning Invariant Representation of Tasks for Robust Surgical State Estimation](https://mlsanity.com/paper/2102.09119/) (2021)
- [Nearest-Neighbor Density Estimation for Dependency Suppression](https://mlsanity.com/paper/2603.04224/) (2026)
- [Advancing the dimensionality reduction of speaker embeddings for speaker diarisation: disentangling noise and informing speech activity](https://mlsanity.com/paper/2110.03380/) (2021)
- [Weakly Supervised Invariant Representation Learning Via Disentangling Known and Unknown Nuisance Factors](https://mlsanity.com/paper/2209.06827/) (2022)
- [Enhancing Multiple Reliability Measures via Nuisance-extended Information Bottleneck](https://mlsanity.com/paper/2303.14096/) (2023)
- [LCIP: Loss-Controlled Inverse Projection of High-Dimensional Image Data](https://mlsanity.com/paper/2602.11141/) (2026)

## Abstract (arXiv)

Data representations that contain all the information about target variables but are invariant to nuisance factors benefit supervised learning algorithms by preventing them from learning associations between these factors and the targets, thus reducing overfitting. We present a novel unsupervised invariance induction framework for neural networks that learns a split representation of data through competitive training between the prediction task and a reconstruction task coupled with disentanglement, without needing any labeled information about nuisance factors or domain knowledge. We describe an adversarial instantiation of this framework and provide analysis of its working. Our unsupervised model outperforms state-of-the-art methods, which are supervised, at inducing invariance to inherent nuisance factors, effectively using synthetic data augmentation to learn invariance, and domain adaptation. Our method can be applied to any prediction task, eg., binary/multi-class classification or regression, without loss of generality.