Research map / Graph learning / GNN architectures
TLAGC: Taylor Linear Attention-Guided Graph Convolutions for Revealing Spatial Domains in Spatial Multi-Omics Data
Aoyun Geng, Chunyan Cui, Yunyun Su, Zhenjie Luo, Feifei Cui, Zilong Zhang
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add Taylor linear attention (ablation) | TLAGC · Human Lymph Node A1 | ARI (%): 27.52 -> 29.49 | Improved |
| add LocalGCN (ablation) | TLAGC · Human Lymph Node A1 | ARI (%): 17.43 -> 29.49 | Improved |
| add spatial KNN graph (ablation) | TLAGC · Human Lymph Node A1 | ARI (%): 13.83 -> 29.49 | Improved |
| add feature KNN graph (ablation) | TLAGC · Human Lymph Node A1 | ARI (%): 24.94 -> 29.49 | Improved |
| add KL clustering loss (ablation) | TLAGC · Human Lymph Node A1 | ARI (%): 25.24 -> 29.49 | Improved |
| add reconstruction loss (ablation) | TLAGC · Human Lymph Node A1 | ARI (%): 28.22 -> 29.49 | Improved |
| replace self-attention with TLA (ablation) | TLAGC · Spatial multi-omics (HLN A1) | GPU memory / training time: -58% memory, -44% training time | Improved |
| use TLA instead of TaylorShift (ablation) | TLAGC · Spatial multi-omics (HLN A1) | clustering quality | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- PRAGA — PRAGA: Prototype-aware Graph Adaptive Aggregation for Spatial Multi-modal Omics Analysis (AAAI 2025) · better on 7 of 7 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- GATCL: An Adaptive Contrastive Learning Framework Based on MHGAT for Spatial Domain Identification in Spatial Transcriptomics (AAAI 2026 · similarity 0.88)
- FEAST: Fully Connected Expressive Attention for Spatial Transcriptomics (CVPR 2026 · similarity 0.88)
- GROVER: Graph-guided Representation of Omics and Vision with Expert Regulation for Adaptive Spatial Multi-omics Fusion (AAAI 2026 · similarity 0.87)
- PRAGA: Prototype-aware Graph Adaptive Aggregation for Spatial Multi-modal Omics Analysis (AAAI 2025 · similarity 0.86)
- Global Context-aware Representation Learning for Spatially Resolved Transcriptomics (ICML 2025 · similarity 0.86)
- SUICA: Learning Super-high Dimensional Sparse Implicit Neural Representations for Spatial Transcriptomics (ICML 2025 · similarity 0.85)
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.
