77 citations · 179 across the 54 of their papers we have counts for
Showing 2026 · cs.LGShow all
2 papers · 2 filters
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…
cs.LG2026
SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks
Yue Xia, Tayyebeh Jahani-Nezhad, Mayank Bakshi +1
We consider federated parameter-efficient fine-tuning of foundation models, e.g., LLMs and LVMs, using low-rank adaptation (LoRA; ~Hu et al.\ 2022). Combining LoRA with federated l…