EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SwarmPNM: A Single-Trajectory Adaptive Optimizer with Positive–Negative Momentum and PSO-Inspired Attraction

Ruslan Abdulkadirov, Nodir Rabimov, Adam Alikhanov, Nabi Aydamirov, Robert Babayan, Ruslan Khairbekov, Nikolay Nagornov, Pavel Lyakhov, Anzhelika Voroshilova, Ekaterina Kopets, Diana Kalita

Big Data and Cognitive Computing · 11.11.2026 · 10 (11) · 384

DOI: 10.3390/bdcc10110384 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Big Data and Cognitive Computing, online erschienen am 11.11.2026. Verfasst von Ruslan Abdulkadirov und 10 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Russian State Assignment.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

SwarmPNM combines an adaptive second-moment estimate and positive–negative gradient momentum with attraction towards the lowest-loss weights stored along a single training trajectory. The attraction is inspired by particle swarm optimization, but the method does not maintain a particle population. We specify the update, analyze the attraction locally under Hessian assumptions and obtain a conditional regret bound for an auxiliary strongly convex projected-gradient model with controlled perturbations. Experiments cover 15 analytic test functions, molecular classification with MolCLR-pretrained GIN and GCN encoders on the blood–brain barrier penetration (BBBP), beta-secretase-1 inhibitor (BACE) and human immunodeficiency virus replication-inhibition (HIV) datasets, and nuclear cross-section regression with a multilayer perceptron. SwarmPNM attains the highest mean ROC–AUC in five of six molecular dataset–encoder combinations. In the four-library nuclear comparison, it has the lowest mean absolute error and the highest coefficient of determination; a separate three-seed nuclear experiment under a different protocol favors AdamW. Repeated-run, sensitivity and ablation studies establish that the contribution of attraction depends on the task and tuning, with the learning rate having the largest observed influence in the analytic sensitivity tests. We also report the additional computational cost relative to AdamW. The auxiliary theory does not establish convergence of the complete nonconvex optimizer.

Förderung

  • Russian State Assignment

Zitieren

APA

Abdulkadirov, R., Rabimov, N., Alikhanov, A., Aydamirov, N., Babayan, R., Khairbekov, R., Nagornov, N., Lyakhov, P., Voroshilova, A., Kopets, E., & Kalita, D. (2026). SwarmPNM: A Single-Trajectory Adaptive Optimizer with Positive–Negative Momentum and PSO-Inspired Attraction. Big Data and Cognitive Computing, 10(11), 384. https://doi.org/10.3390/bdcc10110384

Vancouver

Abdulkadirov R, Rabimov N, Alikhanov A, Aydamirov N, Babayan R, Khairbekov R, et al. SwarmPNM: A Single-Trajectory Adaptive Optimizer with Positive–Negative Momentum and PSO-Inspired Attraction. Big Data and Cognitive Computing. 2026;10(11):384. doi:10.3390/bdcc10110384

BibTeX
@article{Abdulkadirov2026,
  author = {Abdulkadirov, Ruslan and Rabimov, Nodir and Alikhanov, Adam and Aydamirov, Nabi and Babayan, Robert and Khairbekov, Ruslan and Nagornov, Nikolay and Lyakhov, Pavel and Voroshilova, Anzhelika and Kopets, Ekaterina and Kalita, Diana},
  title = {SwarmPNM: A Single-Trajectory Adaptive Optimizer with Positive–Negative Momentum and PSO-Inspired Attraction},
  journal = {Big Data and Cognitive Computing},
  year = {2026},
  volume = {10},
  number = {11},
  pages = {384},
  doi = {10.3390/bdcc10110384}
}
Kostenlos starten →