arXiv：cs.LG（机器学习，全量分类）· Yunhak Oh, Yoonho Lee, Junseok Lee, Namkyeong Lee, Sang-Yeon Hwang, Yinhua Piao, Hyomin Kim, Seonghwan Kim, Jaechang Lim, Woo Youn Kim, Sungsoo Ahn, Chanyoung Park·· 15 小时前AI 评分38
scTrilemma：在单细胞表示学习中平衡身份、不变性与保真度
scTrilemma: Balancing Identity, Invariance, and Fidelity in Single-Cell Representation Learning
AI 导读
针对单细胞 RNA-seq 表示学习中身份、不变性与保真度难以兼顾的"表示三难"问题，研究者提出 scTrilemma——一种潜在瓶颈 VAE，将表达变异分别路由至嵌入、解码器或先验，无需目标注释或辅助表示损失。
正文
Authors:Yunhak Oh, Yoonho Lee, Junseok Lee, Namkyeong Lee, Sang-Yeon Hwang, Yinhua Piao, Hyomin Kim, Seonghwan Kim, Jaechang Lim, Woo Youn Kim, Sungsoo Ahn, Chanyoung Park
Abstract:Single-cell RNA-seq representation learning is fundamentally label-free: cell identities, states, and contexts are not fixed training targets, so what constitutes signal or nuisance is analysis-dependent. A single representation must therefore preserve biological identity and state, remain robust to nuisance context, and retain the gene-level variation needed for expression analysis, three demands we call the representation trilemma. To tackle this problem, we introduce scTrilemma, a latent-bottleneck VAE that routes expression-derived variation to the embedding, the decoder, or the prior rather than forcing all of it through one embedding. It gates gene tokens by expression, routes the cell representation through the decoder, and conditions the prior on unlabeled pseudo-bulk context, under a single reconstruction objective and without target annotations or auxiliary representation losses. In release-based zero-shot evaluation on successive CZ CELLxGENE Census releases, scTrilemma leads all three demands at once and preserves biological-state, differential-expression, and pathway structure across multiple disease settings. Latent interventions further show that context can be removed at almost no cost to the other demands, leaving identity against fidelity as the remaining tension. Code is publicly available at this https URL.
| Comments: | NeurIPS 2026 |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2609.38840 [cs.LG] |
| (or arXiv:2609.38840v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2609.38840 arXiv-issued DOI via DataCite |
Submission history
From: Yunhak Oh [view email]
[v1]
Wed, 30 Sep 2026 02:59:10 UTC (1,165 KB)
[v2]
Thu, 1 Oct 2026 02:34:16 UTC (1,165 KB)
来源：arXiv：cs.LG（机器学习，全量分类） · arxiv.org