Metraipolis › archive › dc_efa050b18882
MoEDDI: Semantic Mixtures of Experts for Long Tailed Drug Drug Interaction Prediction — arXiv:2611.01343
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.01343
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T18:36:50.532Z
- SHA-256 of the archived text
3698bb87e413b1487905c5043d528af7d2cdc8496725245593bb270dd6184479- Stable URL of this page
https://metraipolis.com/documento/dc_efa050b18882
How to cite
MoEDDI: Semantic Mixtures of Experts for Long Tailed Drug Drug Interaction Prediction — arXiv:2611.01343 — arXiv (en), https://arxiv.org/abs/2611.01343 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_efa050b18882 (Metraipolis archive dc_efa050b18882, sha256 3698bb87e413b1487905c5043d528af7d2cdc8496725245593bb270dd6184479)
BibTeX
@misc{dcefa050b18882,
title = {MoEDDI: Semantic Mixtures of Experts for Long Tailed Drug Drug Interaction Prediction — arXiv:2611.01343},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.01343},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_efa050b18882; sha256 3698bb87e413b1487905c5043d528af7d2cdc8496725245593bb270dd6184479},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01343. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Descriptor-based drug--drug interaction (DDI) models typically apply a single global predictor despite heterogeneous physicochemical evidence and severely long-tailed labels. We introduce \textbf{MoEDDI (Mixture-of-Experts for Drug--Drug Interaction prediction)}, a chemically organized mixture-of-experts that routes overlapping descriptor families using low-dimensional statistics and combines their sparse top-$2$ mixture with a global T-DDI pathway through a residual logit correction. The residual parameterization can exactly preserve a supplied T-DDI checkpoint at initialization, although the evaluated models are trained from scratch. Across complete test partitions with 178, 86, and 92 classes, MoEDDI improves macro-F1 over reproduced seed-2026 T-DDI baselines from 0.8284 to 0.8485, 0.4729 to 0.6536, and 0.1807 to 0.4671. On the 3,780-feature corpus, the lowest-support group (89 classes with fewer than 50 test examples) shows the largest mean classwise gain (+3.30 F1 points). Calibration improves on one corpus but worsens on two. These single-seed results support semantic conditional specialization while motivating matched ablations and distribution-shift evaluation.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.01343 — 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 2026-11-03T18:12:54.493Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).