AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Refinement Contrastive Learning of Cell–Gene Associations for Unsupervised Cell Type Identification

Liang Peng, Haopeng Liu, Yixuan Ye, Cheng Liu, Wenjun Shen, Si Wu, Hau-San Wong

AAAI 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add neighborhood distribution contrastive alignment loss (LNDC) (ablation)scRCL · TracheaARI: 64.0 -> 94.8Improved
add cross-view correlation loss (LCVC) (ablation)scRCL · ZeiselARI: 66.4 -> 78.3Improved
add heterogeneous embedding alignment loss (LHEA) (ablation)scRCL · ZeiselARI: 76.6 -> 78.3Improved
add LHEA (ablation)scRCL · Limb MuscleARI: 97.4 -> 99.0Improved
use heterogeneous encoders (GCN + MLP) instead of two GCNs or two MLPs (ablation)scRCL · scRNA-seq datasetsclustering performanceImproved
add gene-informed refinement module (ablation)scRCL · scRNA-seq datasetsclustering performanceImproved
add gene-informed refinement module (ablation)scRCL · Lung marker genesmarker gene specificityImproved
scRCL versus scGCOT, which also uses cell-gene relations for reconstructionscRCL · SpleenARI: 89.70 -> 93.36Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy