asymmetric aggregation 1federated learning 1heterogeneous tasks 1mixture of experts 1parameter-efficient fine-tuning 1
From the 1 of 2 linked papers with an AI index.
2 papers
cs.LG2026
FedWeave: Rethinking the Unit of Specialization in Heterogeneous Federated MoE-LoRA
Donghang Duan, Xu Zheng, Lizong Zhang +2
The paper introduces FedWeave, a federated learning framework that separates expert aggregation from router optimization to better handle heterogeneous tasks by using prototype-lev…
cs.CR2026
Look Twice before You Leap: A Rational Framework for Localized Adversarial Anonymization
Donghang Duan, Xu Zheng, Yuefeng He +3
Current LLM-based frameworks for text anonymization usually rely on remote API services from powerful LLMs, which creates an inherent privacy paradox: users must disclose the raw d…