EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Addressing Long‐Tailed Drug–Drug Interactions Through Minimisation of Predictive Uncertainty and Loss Sharpness

Chao Liu, Xizhao Wang, Farhad Pourpanah, Sam Kwong

CAAI Transactions on Intelligence Technology · 2026-10 · 11 (5) · 1613-1625

DOI: 10.1049/cit2.70166 ↗

Kurz gefasst

Fachartikel in der Zeitschrift CAAI Transactions on Intelligence Technology, online erschienen am 06.08.2026. Verfasst von Chao Liu und 3 weiteren Autor:innen. Die Arbeit nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Drug–Drug Interaction (DDI) prediction is critical for ensuring patient safety, particularly under long‐tailed distributions, where frequent (head) interactions dominate whereas rare (tail) interactions remain underrepresented. Conventional loss functions such as cross‐entropy often tend to overfit head classes while they underperform on rare but clinically important classes. Recent studies have shown that sharpness‐aware minimisation (SAM) improves generalisation by encouraging solutions that lie in flatter regions of the loss landscape. Given that the loss function plays a fundamental role in model training and that uncertainty estimation is crucial for handling ambiguous or difficult samples, we propose the uncertainty and SAM (USAM) loss for improving DDI prediction under long‐tail scenarios. The USAM loss integrates predictive uncertainty with SAM via two key components: (i) a dynamic reweighting strategy based on uncertainty, which leverages prediction entropy to emphasise difficult samples and (ii) a class‐balanced SAM regularisation term, which encourages flatter minima and enhances generalisation across imbalanced classes. Extensive experiments on four long‐tailed DDI benchmarks demonstrate that the USAM loss consistently outperforms existing methods in terms of both F1 score and recall. These results highlight the effectiveness of incorporating uncertainty modelling with sharpness‐aware optimisation in addressing long‐tailed problems.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Liu, C., Wang, X., Pourpanah, F., & Kwong, S. (2026). Addressing Long‐Tailed Drug–Drug Interactions Through Minimisation of Predictive Uncertainty and Loss Sharpness. CAAI Transactions on Intelligence Technology, 11(5), 1613-1625. https://doi.org/10.1049/cit2.70166

Vancouver

Liu C, Wang X, Pourpanah F, Kwong S. Addressing Long‐Tailed Drug–Drug Interactions Through Minimisation of Predictive Uncertainty and Loss Sharpness. CAAI Transactions on Intelligence Technology. 2026;11(5):1613-1625. doi:10.1049/cit2.70166

BibTeX
@article{Liu2026,
  author = {Liu, Chao and Wang, Xizhao and Pourpanah, Farhad and Kwong, Sam},
  title = {Addressing Long‐Tailed Drug–Drug Interactions Through Minimisation of Predictive Uncertainty and Loss Sharpness},
  journal = {CAAI Transactions on Intelligence Technology},
  year = {2026},
  volume = {11},
  number = {5},
  pages = {1613--1625},
  doi = {10.1049/cit2.70166}
}
Kostenlos starten →