Metraipolis › archive › dc_6f50fef0608f
Train to Stitch: Topology-Preserving Regularization for Interoperable Representations — arXiv:2610.19401
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.19401
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T14:15:31.043Z
- SHA-256 of the archived text
afca291b424505e6a458bc65321b568376e2405a0d6ac9a6f71dfd14a4a4e3b1- Stable URL of this page
https://metraipolis.com/documento/dc_6f50fef0608f
How to cite
Train to Stitch: Topology-Preserving Regularization for Interoperable Representations — arXiv:2610.19401 — arXiv (en), https://arxiv.org/abs/2610.19401 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6f50fef0608f (Metraipolis archive dc_6f50fef0608f, sha256 afca291b424505e6a458bc65321b568376e2405a0d6ac9a6f71dfd14a4a4e3b1)
BibTeX
@misc{dc6f50fef0608f,
title = {Train to Stitch: Topology-Preserving Regularization for Interoperable Representations — arXiv:2610.19401},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.19401},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6f50fef0608f; sha256 afca291b424505e6a458bc65321b568376e2405a0d6ac9a6f71dfd14a4a4e3b1},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19401. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Computer Vision and Pattern Recognition (cs.CV); Signal Processing (eess.SP). Pagina del lavoro: https://arxiv.org/abs/2610.19401 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-15T13:53:35.595Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).