3 papers
cs.LG2026
Beyond performance-wise Contribution Evaluation in Federated Learning
Balazs Pejo
Federated learning offers a privacy-friendly collaborative learning framework, yet its success, like any joint venture, hinges on the contributions of its participants. Existing cl…
cs.CR2026
Private and Robust Contribution Evaluation in Federated Learning
Delio Jaramillo Velez, Gergely Biczok, Alexandre Graell i Amat +2
Cross-silo federated learning allows multiple organizations to collaboratively train machine learning models without sharing raw data, but client updates can still leak sensitive i…
cs.LG2025
On the Fragility of Contribution Score Computation in Federated Learning
Balazs Pejo, Marcell Frank, Krisztian Varga +2
This paper investigates the fragility of contribution evaluation in federated learning, a critical mechanism for ensuring fairness and incentivizing participation. We argue that co…