LATIDIA · Investigación

Aprendizaje federado con conciencia de gobernanza para sistemas de IA multiagente: un marco basado en políticas para una IA colaborativa confiable.

arXiv:2610.38411v1 Anuncio Tipo: nuevo Resumen: El aprendizaje federado (FL) permite el entrenamiento colaborativo de modelos sin intercambiar datos brutos, pero el FL convencional proporciona una gobernanza en tiempo de ejecución limitada, verificación de evidencia, fa

La noticia

arXiv:2610.38411v1 Announce Type: new Abstract: Federated Learning (FL) enables collaborative model training without exchanging raw data, but conventional FL provides limited runtime governance, evidence verification, fairness assessment, explainability monitoring, and auditability. This paper proposes Governance-Aware Federated Learning (GAFL), which combines independent governance-evidence verification, temporal trust, fairness and explanation assessment, anomaly detection, policy enforcement, normalized aggregation, and tamper-evident audit logging. Client-reported governance values are authenticated, bound to their submitted model updates, and independently recomputed before aggregation. A cross-silo prototype with 10 participants was evaluated on the Adult Income dataset under honest, benign non-IID, biased-data, malicious-update, non-compliant, falsified-evidence, and mixed-threat scenarios. Four methods were compared across five random seeds: FedAvg, FedAvg with