AI Paper Atlas

Research map / Federated learning and privacy / Personalized and heterogeneous FL

Tensor-aggregated LoRA in Federated Fine-tuning

Zhixuan Li, Binqian Xu, Xiangbo Shu, Jiachao Zhang, Yazhou Yao, Guo-Sen Xie, Jinhui Tang

ICCV 2025 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated prompt and LoRA tuning · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace zero-padding alignment with PAA-strategy (optimal transport) (ablation)Te-LoRA · MMLU Alpaca-GPT4, heterogeneousaccuracy: 44.77 -> 46.16Improved
replace FedAvg weighted average with T2M-strategy (ablation)Te-LoRA · MMLU Alpaca-GPT4, heterogeneousaccuracy: 45.53 -> 46.16Improved
use T2M2 instead of T2M1 (ablation)Te-LoRA · MMLU Alpaca-GPT4, heterogeneousaccuracy: 45.30 -> 46.16Improved
use T2M2 instead of combined T2M3 (ablation)Te-LoRA · MMLU Alpaca-GPT4, heterogeneousaccuracy: 45.99 -> 46.16No clear effect
alternating-freeze training with PAA-strategy but without T2M, versus FlexLoRA (ablation)Te-LoRA · MMLU Alpaca-GPT4, heterogeneousaccuracy: 45.48 -> 45.53Improved
use federated fine-tuning (Te-LoRA) instead of local-only trainingLlama2-7B LoRA · MMLU Alpaca-GPT4, homogeneousaccuracy: 38.66 -> 45.86Improved
move from homogeneous to heterogeneous ranks for Zero-paddingZero-padding · MMLU Wizardaccuracy: 22.03 -> 21.86Hurt
move from homogeneous to heterogeneous ranks for Te-LoRATe-LoRA · MMLU Alpaca-GPT4accuracy: 45.86 -> 46.16 (Alpaca-GPT4), 28.44 -> 28.37 (Dolly)Mixed
alternate-freeze A and B, uploading only one module per roundTe-LoRA · communication cost per roundcommunication costImproved
lower LoRA rank to 4 for all clients (ablation)Local LoRA · MMLU / MT-BenchperformanceHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy