Privacy-sensitive federated learning for cross-domain adaptation: The Mamba-MoE approach

Domain adaptation in decentralized environments poses significant challenges, particularly in privacy-sensitive and resource-constrained scenarios. Conventional approaches, such as Domain-Adversarial Neural Networks (DANN) and Maximum Mean Discrepancy (MMD), rely on large datasets and centralized pr...

Cijeli opis

Bibliografski detalji

Glavni autori:	Muhammad Kashif Jabbar, Huang Jianjun, Ayesha Jabbar, Zaka Ur Rehman
Format:	Artigo
Jezik:	Inglês
Izdano:	Elsevier 2025-09-01
Serija:	Results in Engineering
Teme:	Federated Learning (FL) Mamba-MoE MoE Adaptive routing Privacy-preserving AI Feature fusion
Online pristup:	http://www.sciencedirect.com/science/article/pii/S2590123025025010
Oznake:	Dodaj oznaku Bez oznaka, Budi prvi tko označuje ovaj zapis!