Guided Manifold Alignment with Geometry-Regularized Twin Autoencoders
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912609609973760 |
|---|---|
| author | Rhodes, Jake S. Rustad, Adam G. Nielsen, Marshall S. McClellan, Morgan Chase Gardner, Dallan Hedges, Dawson |
| author_facet | Rhodes, Jake S. Rustad, Adam G. Nielsen, Marshall S. McClellan, Morgan Chase Gardner, Dallan Hedges, Dawson |
| contents | Manifold alignment (MA) involves a set of techniques for learning shared representations across domains, yet many traditional MA methods are incapable of performing out-of-sample extension, limiting their real-world applicability. We propose a guided representation learning framework leveraging a geometry-regularized twin autoencoder (AE) architecture to enhance MA while enabling generalization to unseen data. Our method enforces structured cross-modal mappings to maintain geometric fidelity in learned embeddings. By incorporating a pre-trained alignment model and a multitask learning formulation, we improve cross-domain generalization and representation robustness while maintaining alignment fidelity. We evaluate our approach using several MA methods, showing improvements in embedding consistency, information preservation, and cross-domain transfer. Additionally, we apply our framework to Alzheimer's disease diagnosis, demonstrating its ability to integrate multi-modal patient data and enhance predictive accuracy in cases limited to a single domain by leveraging insights from the multi-modal problem. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_22913 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Guided Manifold Alignment with Geometry-Regularized Twin Autoencoders Rhodes, Jake S. Rustad, Adam G. Nielsen, Marshall S. McClellan, Morgan Chase Gardner, Dallan Hedges, Dawson Machine Learning Manifold alignment (MA) involves a set of techniques for learning shared representations across domains, yet many traditional MA methods are incapable of performing out-of-sample extension, limiting their real-world applicability. We propose a guided representation learning framework leveraging a geometry-regularized twin autoencoder (AE) architecture to enhance MA while enabling generalization to unseen data. Our method enforces structured cross-modal mappings to maintain geometric fidelity in learned embeddings. By incorporating a pre-trained alignment model and a multitask learning formulation, we improve cross-domain generalization and representation robustness while maintaining alignment fidelity. We evaluate our approach using several MA methods, showing improvements in embedding consistency, information preservation, and cross-domain transfer. Additionally, we apply our framework to Alzheimer's disease diagnosis, demonstrating its ability to integrate multi-modal patient data and enhance predictive accuracy in cases limited to a single domain by leveraging insights from the multi-modal problem. |
| title | Guided Manifold Alignment with Geometry-Regularized Twin Autoencoders |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2509.22913 |