Metraipolis › archive › dc_dbf2239f370b

GARLIC: Graph Attention-based Relational Learning of Multivariate Time Series in Intensive Care — arXiv:2608.10969

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.10969
License (as archived)
CC0-1.0
Archived
2026-10-19T06:19:31.578Z
SHA-256 of the archived text
c062935094dbdec0953f4503b0d6bfe5a9ebf27601b8a855c3539cec40f5cc4e
Stable URL of this page
https://metraipolis.com/documento/dc_dbf2239f370b

How to cite

GARLIC: Graph Attention-based Relational Learning of Multivariate Time Series in Intensive Care — arXiv:2608.10969 — arXiv (en), https://arxiv.org/abs/2608.10969 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dbf2239f370b (Metraipolis archive dc_dbf2239f370b, sha256 c062935094dbdec0953f4503b0d6bfe5a9ebf27601b8a855c3539cec40f5cc4e)
BibTeX
@misc{dcdbf2239f370b,
  title = {GARLIC: Graph Attention-based Relational Learning of Multivariate Time Series in Intensive Care — arXiv:2608.10969},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.10969},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dbf2239f370b; sha256 c062935094dbdec0953f4503b0d6bfe5a9ebf27601b8a855c3539cec40f5cc4e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.10969. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Healthcare data, such as Intensive Care Unit (ICU) records, comprise heterogeneous multivariate time series sampled at irregular intervals with pervasive missingness. However, clinical applications demand predictive models that are both accurate and interpretable. We present our Graph Attention-based Relational Learning for Intensive Care (GARLIC) model, a novel neural network architecture that imputes missing data through a learnable exponential-decay encoder, captures inter-sensor dependencies via time-lagged summary graphs, and fuses global patterns with cross-dimensional sequential attention. All attention weights and graph edges are learned end-to-end to serve as built-in observation-, signal-, and edge-level explanations. To reconcile auxiliary reconstruction and primary classification objectives, we developed an alternating decoupled optimization scheme that stabilizes training. On three ICU benchmarks (PhysioNet 2012 & 2019, MIMIC-III), GARLIC sets the new state of the art in outcome prediction, significantly improving AUROC and AUPRC over best-performing baselines at comparable computational cost. Ablation studies confirm the contribution of each module, and feature-removal trials validate the fidelity of importance attribution through a monotonic performance drop (full > top 50% > random 50% > bottom 50%). Real-time case studies demonstrate actionable risk warnings with transparent explanations, marking a significant advance toward accurate, explainable deep learning for irregularly sampled ICU time series data. Moreover, we demonstrated \proposed{}'s superiority in data imputation and classification on various time-series datasets beyond the ICU domain, showing its generalizability and applicability to broader tasks.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-12 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.10969 — 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 2026-10-19T06:11:45.103Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).