Metraipolis › archive › dc_84fd10339dfe
Disentangled Shared Representations Improve Morpho-Transcriptomic Integration — arXiv:2608.14355
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.14355
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T02:20:47.643Z
- SHA-256 of the archived text
418b6fbcdf8bf58599d23f3fdcef37f2321ed03e2a832dce329d7f0bff78a239- Stable URL of this page
https://metraipolis.com/documento/dc_84fd10339dfe
How to cite
Disentangled Shared Representations Improve Morpho-Transcriptomic Integration — arXiv:2608.14355 — arXiv (en), https://arxiv.org/abs/2608.14355 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_84fd10339dfe (Metraipolis archive dc_84fd10339dfe, sha256 418b6fbcdf8bf58599d23f3fdcef37f2321ed03e2a832dce329d7f0bff78a239)
BibTeX
@misc{dc84fd10339dfe,
title = {Disentangled Shared Representations Improve Morpho-Transcriptomic Integration — arXiv:2608.14355},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.14355},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_84fd10339dfe; sha256 418b6fbcdf8bf58599d23f3fdcef37f2321ed03e2a832dce329d7f0bff78a239},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14355. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Spatial transcriptomics (ST) enables the simultaneous profiling of gene expression and tissue morphology, creating an opportunity to learn multimodal representations capturing shared morpho-transcriptomic structure. However, standard multimodal models often compress modalities into a common latent space without explicitly separating shared and modality-specific sources of variation, which may limit downstream utility. We investigate whether explicit disentanglement of shared and private latent components improves multimodal representation learning for paired Hematoxylin \& Eosin (H\&E) and ST data. We compare VAE-based and contrastive approaches, each in standard and disentangled variants, across two cancer cohorts under matched experimental conditions. Representations are evaluated using cross-modal reconstruction, downstream probing and cross-modal probe transfer. The experiments suggest two main trends. First, contrastive objectives yield higher downstream probing performance than VAE-based models. Second, disentangled variants improve the selected reconstruction and probing metrics, although the gains depend on the model family, task, direction, and disentanglement strength. Overall, our results suggest that explicitly factorizing shared and modality-specific information can improve multimodal representation learning for spatial transcriptomics and provides a useful evaluation framework for future foundation models. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-17 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.14355 — 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 2026-10-19T02:02:02.810Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).