Decentralized Federated Learning with Multimodal Prototypes for Heterogeneous Data
Datos rápidos
- Año
- 2026
- Venue
- Information Fusion
- Identificador
- martinezbeltran2026decentralized
Cita sugerida
Enrique Tomás Martínez Beltrán, Gérôme Bovet, Gregorio Martínez Pérez, Alberto Huertas Celdrán (2026). Decentralized Federated Learning with Multimodal Prototypes for Heterogeneous Data. Information Fusion.
Resumen
Autores
Palabras clave
Publicaciones relacionadas
Trabajos cercanos por temática, tipo y solapamiento de etiquetas.
Asynchronous Cache-based Aggregation with Fairness and Filtering for Decentralized Federated Learning
Enrique Tomás Martínez Beltrán, Eduard Gash, Gérôme Bovet, Alberto Huertas Celdrán, Burkhard Stiller
Decentralized Federated Learning (DFL) offers a scalable paradigm for collaborative intelligence at the edge, yet its practical efficacy is severely constrained by system heterogeneity. Traditional synchronous protocols enforce rigid, locks...
Analyzing the impact of Driving tasks when detecting emotions through brain--computer interfaces
Mario Quiles Pérez, Enrique Tomás Martínez Beltrán, Sergio López Bernal, Gregorio Martínez Pérez, Alberto Huertas Celdrán
Traffic accidents are the leading cause of death among young people, a problem that today costs an enormous number of victims. Several technologies have been proposed to prevent accidents, being brain--computer interfaces (BCIs) one of the...
Analyzing the robustness of decentralized horizontal and vertical federated learning architectures in a non-IID scenario
Pedro Miguel Sánchez Sánchez, Alberto Huertas Celdrán, Enrique Tomás Martínez Beltrán, Daniel Demeter, Gérôme Bovet, Gregorio Martínez Pérez, Burkhard Stiller
Federated learning (FL) enables participants to collaboratively train machine and deep learning models while safeguarding data privacy. However, the FL paradigm still has drawbacks that affect its trustworthiness, as malicious participants...
Investigación relacionada
Abr 2023 — Nov 2023
DEFENDIS: aprendizaje federado descentralizado para identificación y seguridad de dispositivos IoT
DEFENDIS desarrolla un marco para identificar de forma distribuida dispositivos IoT y abordar amenazas de seguridad mediante aprendizaje federado descentralizado.
Dic 2022 — Nov 2025
EU-GUARDIAN: marco europeo y pruebas de concepto para la automatización inteligente de la gestión de incidentes de ciberdefensa
Solución avanzada basada en IA para automatizar la gestión de incidentes de ciberdefensa y reforzar la postura y las capacidades operativas de ciberdefensa de la UE.