# Train to Stitch: Topology-Preserving Regularization for Interoperable Representations

arXiv: https://arxiv.org/abs/2610.19401 · HTML: https://mlsanity.com/paper/2610.19401/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 29 references that are in the map.
- First posted on arXiv 14 Oct 2026.

## Builds on (most cited first, 14 of 14)

- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [End-to-end Optimized Image Compression](https://mlsanity.com/paper/1611.01704/) (2016)
- [Relative representations enable zero-shot latent space communication](https://mlsanity.com/paper/2209.15430/) (2022)
- [Latent Space Oddity: on the Curvature of Deep Generative Models](https://mlsanity.com/paper/1710.11379/) (2017)
- [Conditional Probability Models for Deep Image Compression](https://mlsanity.com/paper/1801.04260/) (2018)
- [Topological Autoencoders](https://mlsanity.com/paper/1906.00722/) (2019)
- [Latent Space Translation via Semantic Alignment](https://mlsanity.com/paper/2311.00664/) (2023)
- [Low Bit-Rate Speech Coding with VQ-VAE and a WaveNet Decoder](https://mlsanity.com/paper/1910.06464/) (2019)
- [FS-COCO: Towards Understanding of Freehand Sketches of Common Objects in Context](https://mlsanity.com/paper/2203.02113/) (2022)
- [From Bricks to Bridges: Product of Invariances to Enhance Latent Space Communication](https://mlsanity.com/paper/2310.01211/) (2023)
- [An Overview of the 3GPP Study on Artificial Intelligence for 5G New Radio](https://mlsanity.com/paper/2308.05315/) (2023)
- [A Geometric Perspective on Autoencoders](https://mlsanity.com/paper/2309.08247/) (2023)
- [Back To The Drawing Board: Rethinking Scene-Level Sketch-Based Image Retrieval](https://mlsanity.com/paper/2509.06566/) (2025)

## Abstract (arXiv)

As large, powerful pre-trained models become more prevalent, there is growing interest in developing methods that allow different neural networks to be seamlessly combined with little or no direct communication between them. Take autoencoder-based data compression as an example: the ability to independently choose architectures and train encoder and decoder models, while still ensuring they work together, could fundamentally transform how such models are built, deployed, and updated. In this work, we introduce a novel approach that leverages topological regularization to align the latent spaces of two independently trained autoencoder models, entirely eliminating the need for coordination during training. We provide a conditional theoretical analysis showing how the structural agreement encouraged by our regularizer can translate into approximate geometric compatibility between independently learned representations. Reconstruction experiments validate this approach empirically, substantially narrowing the interoperability gap across multiple datasets.