Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Multi-Token Random-Walk Learning via Meeting-Triggered Information Exchange
Taichun Yeh, Xingran Chen
Random walk (RW)-based algorithms are widely used in decentralized learning due to their low communication overhead and scalability. While most existing methods rely on a single to…
cs.LG2026
RW-LoRA: Communication-Efficient Decentralized LoRA Fine-Tuning via Random Walks
Xingran Chen, Rohit Bhagat, Ghadir Ayache +3
Parameter-efficient fine-tuning methods such as LoRA have become a standard approach for adapting large foundation models. Adopting fine-tuning to distributed settings faces severa…