Core Concepts
Die Entwicklung eines Topologie-Lernverfahrens zur Verbesserung des dezentralen föderierten Lernens über unzuverlässige D2D-Netzwerke.
Stats
"Extensive experiments under both feature skew and label skew settings have validated the effectiveness of our proposed method, demonstrating improved convergence speed and test accuracy, consistent with our theoretical findings."
"The size of transmitted packages is set to 1.2MB."
"The bandwidth is set to 5MHz, the transmission power Ptx is set to 10dBm and the noise power σ2 is set to −169dBm."
Quotes
"Decentralized federated learning with unreliable communications."
"Joint scheduling and robust aggregation for federated localization over unreliable wireless D2D networks."