AI Paper Atlas

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

FedRot-LoRA: Mitigating Rotational Misalignment in Federated LoRA

Haoran Zhang, Dongjun Kim, Seohyeon Cha, Haris Vikalo

ICML 2026 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated prompt and LoRA tuning · 0 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
add Procrustes rotational alignment before factor averagingFedIT · GLUE avg (N=50, r=4)accuracy: 0.7680 -> 0.8734Improved
add rotational alignmentFedIT · MNLI aggregation erroraggregation error: 3.98e-3 -> 1.48e-4Improved
replace alignment with random orthogonal rotations (ablation)FedRot-LoRA · MNLIaccuracy: 0.876 -> 0.3181Hurt
alternate alignment between A and B instead of aligning only A (ablation)FedRot-LoRA · SST-2, QNLI, MNLIaccuracy: MNLI 0.861 -> 0.876Improved
alternate alignment between A and B instead of aligning only B (ablation)FedRot-LoRA · QNLIaccuracy: 0.806 -> 0.926Improved
use intermediate soft rotation lambda rather than lambda=1.0 or 0 (ablation)FedRot-LoRA · MNLI, QQPaccuracyImproved
increase LoRA rank to 16 and 24 (ablation)RoLoRA · MNLI (N=3)accuracy: 0.869 (r=8) -> 0.722 (r=16)Hurt
increase LoRA rank from 4 to 24 (ablation)FedRot-LoRA · MNLI (N=3)accuracy: 0.876 -> 0.872No clear effect
increase data heterogeneity (h from 100 to 0.5) (ablation)FedRot-LoRA · MNLIaccuracy: 0.884 -> 0.876Hurt
increase number of clients from 3 to 50 (ablation)FedIT · GLUE avgaccuracy: 0.8712 -> 0.7680Hurt
increase number of clients from 3 to 50 (ablation)FedRot-LoRA · GLUE avgaccuracy: 0.8932 -> 0.8734Hurt
add rotational alignmentFedIT · GLUE QQP (N=3)accuracy: 0.771 -> 0.842Improved

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