EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Reputation-Coupled Incentives for Federated Learning: A Budget-Matched Simulation Study under Strategic Participation

Seyyed Ahmad Edalatpanah, Dragan Pamucar, Robert S. Keyser

Systemic Analytics · 19.12.2026 · 4 (4) · 278-290

DOI: 10.31181/sa44202697 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Systemic Analytics, online erschienen am 19.12.2026. Verfasst von Seyyed Ahmad Edalatpanah und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We examine reputation-coupled reward sharing in a federated-learning simulation with heterogeneous client costs, stochastic availability, and strategic populations. RePStack combines a grid-based leader budget choice, myopic mean-field effort responses, contribution estimates, and exponentially smoothed reputation; no repeated-game equilibrium is established. The reported campaign comprises 189 trials on Fashion-MNIST and a tinyshakespeare subset, with 60 clients and 40 rounds. Across 20 dataset–cost–seed blocks, RePStack has lower final monitored accuracy than contribution-only sharing (mean difference −0.0399; reported Holm-adjusted p = 0.019), and lower effective participation than flat and reputation-only sharing (differences −0.179 and −0.173; reported adjusted p = 7.6 × 10⁻⁶). These estimates pool heterogeneous workloads. Strategist–truthful utility contrasts are positive for free-riders under contribution-only and hybrid sharing (+3.13 and +2.13 budget units), but are not matched counterfactual deviation gains. Three-seed strategic tests cannot establish immunity or equivalence. The reputation-exponent ablation reports increasing welfare from 320 to 518 units and decreasing participation from 0.068 to 0.021; accuracy is not monotone. The results support a model-specific participation trade-off. Untouched-test generalization, settlement accounting, inferential outputs, and reproducibility require the original experimental records.

Zitieren

APA

Edalatpanah, S. A., Pamucar, D., & Keyser, R. S. (2026). Reputation-Coupled Incentives for Federated Learning: A Budget-Matched Simulation Study under Strategic Participation. Systemic Analytics, 4(4), 278-290. https://doi.org/10.31181/sa44202697

Vancouver

Edalatpanah SA, Pamucar D, Keyser RS. Reputation-Coupled Incentives for Federated Learning: A Budget-Matched Simulation Study under Strategic Participation. Systemic Analytics. 2026;4(4):278-290. doi:10.31181/sa44202697

BibTeX
@article{Edalatpanah2026,
  author = {Edalatpanah, Seyyed Ahmad and Pamucar, Dragan and Keyser, Robert S.},
  title = {Reputation-Coupled Incentives for Federated Learning: A Budget-Matched Simulation Study under Strategic Participation},
  journal = {Systemic Analytics},
  year = {2026},
  volume = {4},
  number = {4},
  pages = {278--290},
  doi = {10.31181/sa44202697}
}
Kostenlos starten →