Metraipolis › archive › dc_19c8b96cb5a2
Pheno-GS: Phenoscape-scale Geodesic Sinkhorn — arXiv:2609.27633
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.27633
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T10:57:15.171Z
- SHA-256 of the archived text
03a9a8db7192ce6122d3dbd38bd03eb866f7b883f8e649a8d485db6d49cbf9be- Stable URL of this page
https://metraipolis.com/documento/dc_19c8b96cb5a2
How to cite
Pheno-GS: Phenoscape-scale Geodesic Sinkhorn — arXiv:2609.27633 — arXiv (en), https://arxiv.org/abs/2609.27633 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_19c8b96cb5a2 (Metraipolis archive dc_19c8b96cb5a2, sha256 03a9a8db7192ce6122d3dbd38bd03eb866f7b883f8e649a8d485db6d49cbf9be)
BibTeX
@misc{dc19c8b96cb5a2,
title = {Pheno-GS: Phenoscape-scale Geodesic Sinkhorn — arXiv:2609.27633},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.27633},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_19c8b96cb5a2; sha256 03a9a8db7192ce6122d3dbd38bd03eb866f7b883f8e649a8d485db6d49cbf9be},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.27633. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
High-throughput single-cell data is now collected across large patient cohorts. Understanding patient-level heterogeneity from cellular-level data motivates phenoscaping: embedding each single-cell distribution as a "datapoint," with distances given by optimal transport (OT). Computing geometry-aware OT at this scale, between all pairs of patient datasets, remains an open challenge, since existing methods either rely on Euclidean ground metrics that distort manifold structure or fail under sparse, unevenly sampled, or large-scale data. We present \textbf{Pheno-GS} (Phenoscape-scale Geodesic Sinkhorn), which computes accurate, scalable geodesic transport distances under noisy, unbalanced, large-scale settings via three components: ($1$) graph connectivity regularization for well-defined geodesics on sparse/disconnected manifolds; ($2$) an unbalanced OT formulation via KL marginal penalties; and ($3$) a batched matrix algorithm computing all pairwise distances in one heat diffusion (over $200 \times$ faster than Geodesic Sinkhorn for $500$ distributions). We validate Pheno-GS on synthetic benchmarks and a CyTOF perturbation dataset.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-24 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Quantitative Methods (q-bio.QM).
Pagina del lavoro: https://arxiv.org/abs/2609.27633 — 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 2026-10-08T10:06:16.739Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).