# Learning Autoencoders with Relational Regularization

arXiv: https://arxiv.org/abs/2002.02913 · HTML: https://mlsanity.com/paper/2002.02913/

## Key facts

- Cited by 20 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 7 Feb 2020.

## Built on by (most cited first, 20 of 20)

- [ADD: Frequency Attention and Multi-View based Knowledge Distillation to Detect Low-Quality Compressed Deepfake Images](https://mlsanity.com/paper/2112.03553/) (2021)
- [Unbalanced Optimal Transport, from Theory to Numerics](https://mlsanity.com/paper/2211.08775/) (2022)
- [Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety](https://mlsanity.com/paper/2104.14235/) (2021)
- [Hilbert Curve Projection Distance for Distribution Comparison](https://mlsanity.com/paper/2205.15059/) (2022)
- [Auto-regressive Image Synthesis with Integrated Quantization](https://mlsanity.com/paper/2207.10776/) (2022)
- [Enhancing Unsupervised Anomaly Detection with Score-Guided Network](https://mlsanity.com/paper/2109.04684/) (2021)
- [ReGuLaR: Variational Latent Reasoning Guided by Rendered Chain-of-Thought](https://mlsanity.com/paper/2601.23184/) (2026)
- [Gromov-Wasserstein Autoencoders](https://mlsanity.com/paper/2209.07007/) (2022)
- [Meta-Learning for Unsupervised Outlier Detection with Optimal Transport](https://mlsanity.com/paper/2211.00372/) (2022)
- [Personalised Federated Learning On Heterogeneous Feature Spaces](https://mlsanity.com/paper/2301.11447/) (2023)
- [Learning Graphon Autoencoders for Generative Graph Modeling](https://mlsanity.com/paper/2105.14244/) (2021)
- [EfficientTDNN: Efficient Architecture Search for Speaker Recognition](https://mlsanity.com/paper/2103.13581/) (2021)
- [MoReL: Multi-omics Relational Learning](https://mlsanity.com/paper/2203.08149/) (2022)
- [COEM: Cross-Modal Embedding for MetaCell Identification](https://mlsanity.com/paper/2207.07734/) (2022)
- [Regularized Optimal Transport Layers for Generalized Global Pooling Operations](https://mlsanity.com/paper/2212.06339/) (2022)
- [Fast Gradient Computation for Gromov-Wasserstein Distance](https://mlsanity.com/paper/2404.08970/) (2024)
- [Hybrid Gromov-Wasserstein Embedding for Capsule Learning](https://mlsanity.com/paper/2209.00232/) (2022)
- [Keypoint-Guided Optimal Transport: Models, Algorithms, and Applications](https://mlsanity.com/paper/2303.13102/) (2023)
- [An Information-Theoretic Regularizer for Lossy Neural Image Compression](https://mlsanity.com/paper/2411.16727/) (2024)
- [Optimizing Latent Dimension Allocation in Hierarchical VAEs: Balancing Attenuation and Information Retention for OOD Detection](https://mlsanity.com/paper/2506.10089/) (2025)

## Abstract (arXiv)

A new algorithmic framework is proposed for learning autoencoders of data distributions. We minimize the discrepancy between the model and target distributions, with a relational regularization on the learnable latent prior. This regularization penalizes the fused Gromov-Wasserstein (FGW) distance between the latent prior and its corresponding posterior, allowing one to flexibly learn a structured prior distribution associated with the generative model. Moreover, it helps co-training of multiple autoencoders even if they have heterogeneous architectures and incomparable latent spaces. We implement the framework with two scalable algorithms, making it applicable for both probabilistic and deterministic autoencoders. Our relational regularized autoencoder (RAE) outperforms existing methods, e.g., the variational autoencoder, Wasserstein autoencoder, and their variants, on generating images. Additionally, our relational co-training strategy for autoencoders achieves encouraging results in both synthesis and real-world multi-view learning tasks. The code is at https://github.com/HongtengXu/ Relational-AutoEncoders.