AI Paper Atlas

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

Shift-Dependent Asymmetry: Orthogonal Inverse Low-Rank Adaptation for Federated Medical Segmentation

Xingyue Zhao, Wenke Huang, Linghao Zhuang, Haoran Wu, Anwen Jiang, Zhifeng Wang, Wenwen He, Ming Feng, Mang Ye, Bo XU

ICML 2026 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated medical and multimodal learning · 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 Inverse Asymmetric Tuning (local-A/shared-B in encoder, shared-A/local-B in decoder) (ablation)Federated LoRA on SAM · Fundus OD/OC avgDSC: 77.33 -> 83.47Improved
Add Subspace Orthogonality Regularizer on top of IAT (ablation)FedIAT · Fundus OD/OC avgDSC: 83.47 -> 84.52Improved
Add IAT on DRISHTI-GS1 client (ablation)Federated LoRA on SAM · Fundus DRISHTI-GS1DSC: 57.74 -> 81.64Improved
Add SOR on top of IAT on REFUGE and G1020 (ablation)FedIAT · Fundus REFUGE and G1020DSC: REFUGE 89.13 -> 89.00; G1020 77.71 -> 78.15Mixed
Reverse allocation rule (opposite of IAT) (ablation)FedIAT · Fundus OD/OC avgDSC: 83.47 -> 82.54Hurt
Use inverse allocation instead of uniform sharing (FedSA) (ablation)FedIAT · Fundus OD/OC avgDSC: 83.04 -> 83.47Improved
Set SOR weight lambda to 1e-4 instead of negligible 1e-6 (ablation)FedIAT · Histology and FundusDSC: 81.40 (Histology), 84.52 (Fundus) at lambda 1e-4Improved
Set SOR weight lambda to overly large 1e-3 (ablation)FedIAT · Histology and FundusDSCHurt
Apply LoRA to encoder and decoder instead of encoder only (ablation)LoRA on SAM · Medical segmentation (preliminary)DSCImproved
Freeze LoRA A factor (FFA-LoRA) instead of aggregatingFederated LoRA · Histology TNBC clientDSC: 3.59 on TNBCHurt
Increase LoRA rank from 8 to 16FedIAT · Histology nuclei avgDSC: 81.40 -> 81.49No clear effect
Share only one LoRA factor instead of bothFedIAT · Per-round communicationCommunicated params: 0.78M -> 0.55MImproved

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