About this document

Multilingual Federated Learning for 6G by Malik Anis is a document available to read on EtoBox.

This paper introduces a federated learning framework that combines a compact multilingual small language model with multimodal data processing for edge intelligence in 6G networks, achieving 95.6% classification accuracy and significant energy savings. The system utilizes a 1.3 billion parameter mT5-small architecture, incorporates language-aware client selection, and employs reinforcement learning for optimizing resource usage. The proposed approach outperforms centralized models and single-language federa

Author

Malik Anis

Language

EN