AI Paper Atlas

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

Multi-Modal Style Transfer-based Prompt Tuning for Efficient Federated Domain Generalization

Yuliang Chen, Xi Lin, Jun Wu, Xiangrui Cai, Qiaolun Zhang, Xichun Fan, Jiapeng Xu, Xiu Su

AAAI 2026 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated prompt and LoRA tuning · 2 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 multi-modal style transfer (MST) to global-prompt variant (ablation)FaST-PT · PACS ablation (average over 4 target domains)average accuracy: 92.58 -> 94.38Improved
add MST to global+domain prompts with DPG (ablation)FaST-PT · PACS ablation (average over 4 target domains)average accuracy: 97.06 -> 98.16Improved
add contrastive loss between global and domain prompts (ablation)FaST-PT · PACS ablation (average over 4 target domains)average accuracy: 97.95 -> 98.16Improved
combine global and domain prompts instead of either alone (ablation)FaST-PT · PACS ablation (average over 4 target domains)average accuracy: 87.67 -> 97.06Improved
add target-domain text description for augmentation (ablation)FaST-PT · PACS ablation (average over 4 target domains)average accuracy: 98.16 -> 98.42No clear effect
increase prompt length beyond 4 (ablation)FaST-PT · PACS and DomainNetaccuracyMixed
FaST-PT vs DiPromptFaST-PT · PACS averageaccuracy: 94.86 -> 98.16Improved
FaST-PT vs DiPromptFaST-PT · DomainNet averageaccuracy: 86.84 -> 89.17Improved
FaST-PT vs DiPromptFaST-PT · VLCS C domainaccuracy: 99.70 -> 99.17Hurt
use prompt exchange instead of full model uploadFaST-PT · communicationuploaded parameters: 305M -> 0.005MImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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