EUVIMEDEUVIMED entdecken
Crossref

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

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (25) · 21269-21277

DOI: 10.1609/aaai.v40i25.39272 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Aoyun Geng und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the rapid advance of spatial multi-omics technologies, it has become possible to simultaneously profile transcripts, proteins and chromatin states at their native spatial coordinates, thereby uncovering molecular architecture that transcends any single-omics perspective. However, the resulting data matrices are often highly sparse and suffer from unstable dimensionality. Graph-based neural methods capture only local neighborhood information, whereas conventional Transformers, although capable of modelling long-range dependencies, incur prohibitive computational costs on such data. To overcome these limitations, we propose TLAGC—a Taylor-Linear-Attention-Guided Graph Convolutional framework that couples a Taylor-expanded linear attention (TLA) mechanism with graph convolutional networks. By eliminating the soft-max operation and linking the LocalGCN via residual connections, TLA preserves local structural information while enabling the integration of global and local contexts, thereby alleviating ineffective information propagation between spatially distant yet transcriptionally similar regions. Theoretical analysis confirms that TLA indeed reduces computational complexity, and extensive experiments on multiple spatial multi-omics benchmarks demonstrate that TLAGC consistently outperforms state-of-the-art baselines in delineating spatial domains.

Zitieren

APA

Geng, A., Cui, C., Su, Y., Luo, Z., Cui, F., & Zhang, Z. (2026). TLAGC: Taylor Linear Attention-Guided Graph Convolutions for Revealing Spatial Domains in Spatial Multi-Omics Data. Proceedings of the AAAI Conference on Artificial Intelligence, 40(25), 21269-21277. https://doi.org/10.1609/aaai.v40i25.39272

Vancouver

Geng A, Cui C, Su Y, Luo Z, Cui F, Zhang Z. TLAGC: Taylor Linear Attention-Guided Graph Convolutions for Revealing Spatial Domains in Spatial Multi-Omics Data. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(25):21269-21277. doi:10.1609/aaai.v40i25.39272

BibTeX
@article{Geng2026,
  author = {Geng, Aoyun and Cui, Chunyan and Su, Yunyun and Luo, Zhenjie and Cui, Feifei and Zhang, Zilong},
  title = {TLAGC: Taylor Linear Attention-Guided Graph Convolutions for Revealing Spatial Domains in Spatial Multi-Omics Data},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {25},
  pages = {21269--21277},
  doi = {10.1609/aaai.v40i25.39272}
}
Kostenlos starten →