arXiv：cs.LG· Akshay Malhotra, Nicolas Zilberstein, Shahab Hamidi-Rad·· 2 小时前
Train to Stitch：用拓扑保持正则化实现自编码器表示互通
Train to Stitch: Topology-Preserving Regularization for Interoperable Representations
AI 导读
研究者提出 Train to Stitch，用拓扑正则化对齐两个独立训练的自编码器模型的隐空间，训练全程无需任何协调。该方法给出条件性理论分析，说明正则项鼓励的结构一致性可转化为独立学习表示间的近似几何兼容。重建实验在多个数据集上大幅缩小了互操作差距。
正文
Abstract: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.
| Subjects: | Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV); Signal Processing (eess.SP) |
| Cite as: | arXiv:2610.19401 [cs.LG] |
| (or arXiv:2610.19401v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.19401 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Akshay Malhotra [view email]
[v1]
Wed, 14 Oct 2026 01:49:40 UTC (258 KB)
来源：arXiv：cs.LG · arxiv.org