# Understanding and Improving Interpolation in Autoencoders via an Adversarial Regularizer

arXiv: https://arxiv.org/abs/1807.07543 · HTML: https://mlsanity.com/paper/1807.07543/

## Key facts

- Cited by 88 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jul 2018.

## Built on by (most cited first, 30 of 88)

- [Neural-PIL: Neural Pre-Integrated Lighting for Reflectance Decomposition](https://mlsanity.com/paper/2110.14373/) (2021)
- [A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challenges](https://mlsanity.com/paper/2110.14051/) (2021)
- [Fair Mixup: Fairness via Interpolation](https://mlsanity.com/paper/2103.06503/) (2021)
- [Deep Clustering: A Comprehensive Survey](https://mlsanity.com/paper/2210.04142/) (2022)
- [Deep One-Class Classification via Interpolated Gaussian Descriptor](https://mlsanity.com/paper/2101.10043/) (2021)
- [Constrained Contrastive Distribution Learning for Unsupervised Anomaly Detection and Localisation in Medical Images](https://mlsanity.com/paper/2103.03423/) (2021)
- [VQ-GNN: A Universal Framework to Scale up Graph Neural Networks using Vector Quantization](https://mlsanity.com/paper/2110.14363/) (2021)
- [Smoothing the Disentangled Latent Style Space for Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/2106.09016/) (2021)
- [AlignMixup: Improving Representations By Interpolating Aligned Features](https://mlsanity.com/paper/2103.15375/) (2021)
- [A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainability](https://mlsanity.com/paper/2212.10888/) (2022)
- [SoftHebb: Bayesian Inference in Unsupervised Hebbian Soft Winner-Take-All Networks](https://mlsanity.com/paper/2107.05747/) (2021)
- [MATLABER: Material-Aware Text-to-3D via LAtent BRDF auto-EncodeR](https://mlsanity.com/paper/2308.09278/) (2023)
- [Embracing the Dark Knowledge: Domain Generalization Using Regularized Knowledge Distillation](https://mlsanity.com/paper/2107.02629/) (2021)
- [Pythae: Unifying Generative Autoencoders in Python -- A Benchmarking Use Case](https://mlsanity.com/paper/2206.08309/) (2022)
- [It Takes Two to Tango: Mixup for Deep Metric Learning](https://mlsanity.com/paper/2106.04990/) (2021)
- [Self-supervised Pseudo Multi-class Pre-training for Unsupervised Anomaly Detection and Segmentation in Medical Images](https://mlsanity.com/paper/2109.01303/) (2021)
- [Interpolation-based Contrastive Learning for Few-Label Semi-Supervised Learning](https://mlsanity.com/paper/2202.11915/) (2022)
- [MUM : Mix Image Tiles and UnMix Feature Tiles for Semi-Supervised Object Detection](https://mlsanity.com/paper/2111.10958/) (2021)
- [A Survey on Mixup Augmentations and Beyond](https://mlsanity.com/paper/2409.05202/) (2024)
- [Few-shot Image Generation with Mixup-based Distance Learning](https://mlsanity.com/paper/2111.11672/) (2021)
- [Ten Years of Generative Adversarial Nets (GANs): A survey of the state-of-the-art](https://mlsanity.com/paper/2308.16316/) (2023)
- [Motion Planning by Learning the Solution Manifold in Trajectory Optimization](https://mlsanity.com/paper/2107.05842/) (2021)
- [On the relation between statistical learning and perceptual distances](https://mlsanity.com/paper/2106.04427/) (2021)
- [Synthesising Multi-Modal Minority Samples for Tabular Data](https://mlsanity.com/paper/2105.08204/) (2021)
- [Learning cortical representations through perturbed and adversarial dreaming](https://mlsanity.com/paper/2109.04261/) (2021)
- [An Embarrassingly Simple Consistency Regularization Method for Semi-Supervised Medical Image Segmentation](https://mlsanity.com/paper/2202.00677/) (2022)
- [Deep hybrid model with satellite imagery: how to combine demand modeling and computer vision for behavior analysis?](https://mlsanity.com/paper/2303.04204/) (2023)
- [Is Disentanglement enough? On Latent Representations for Controllable Music Generation](https://mlsanity.com/paper/2108.01450/) (2021)
- [Generative AI for Urban Planning: Synthesizing Satellite Imagery via Diffusion Models](https://mlsanity.com/paper/2505.08833/) (2025)
- [Autoencoding Low-Resolution MRI for Semantically Smooth Interpolation of Anisotropic MRI](https://mlsanity.com/paper/2202.09258/) (2022)

## Abstract (arXiv)

Autoencoders provide a powerful framework for learning compressed representations by encoding all of the information needed to reconstruct a data point in a latent code. In some cases, autoencoders can "interpolate": By decoding the convex combination of the latent codes for two datapoints, the autoencoder can produce an output which semantically mixes characteristics from the datapoints. In this paper, we propose a regularization procedure which encourages interpolated outputs to appear more realistic by fooling a critic network which has been trained to recover the mixing coefficient from interpolated data. We then develop a simple benchmark task where we can quantitatively measure the extent to which various autoencoders can interpolate and show that our regularizer dramatically improves interpolation in this setting. We also demonstrate empirically that our regularizer produces latent codes which are more effective on downstream tasks, suggesting a possible link between interpolation abilities and learning useful representations.