mlsanityData to 14 Oct 2026

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

arXiv 2606.08687 ↗First posted 7 Jun 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Low-Rank Adaptation (LoRA) enables efficient federated fine-tuning of segmentation foundation models for medical imaging. However, most federated LoRA methods adopt a uniform aggregation rule, which breaks under the encoder-decoder asymmetry in medical segmentation: the encoder is dominated by appearance shifts, while the decoder is dominated by supervision variations. This mismatch entangles shared anatomy with site-specific biases and harms generalization. To address this, we propose Inverse Asymmetric Tuning (IAT). IAT aligns adaptation with heterogeneity sources by personalizing module-specific components in the encoder to absorb appearance shifts and in the decoder to accommodate site-dependent supervision, while retaining a shared pathway for transferable consensus. However, structural separation alone is insufficient under LoRA's bilinear parameterization, where multiplicative coupling can still cause site-specific updates to leak into the shared direction. We therefore introduce a Subspace Orthogonality Regularizer that penalizes shared-local collinearity in the effective update space, mitigating leakage without extra communication. Experiments show consistent improvements over strong federated LoRA and parameter-efficient FL baselines.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 39 of its 58 references that are in the map. First posted on arXiv 7 Jun 2026.

Builds on

39 of 58 references.

References · 39

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  2. 2023Segment Anythingcited by 8,234
  3. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  4. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,236
  5. 2019Advances and Open Problems in Federated Learningcited by 3,046
  6. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,229
  7. 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 906
  8. 2022Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learningcited by 896
  9. 2021Model-Contrastive Federated Learningcited by 766
  10. 2021FedBN: Federated Learning on Non-IID Features via Local Batch Normalizationcited by 571
  11. 2021Exploiting Shared Representations for Personalized Federated Learningcited by 541
  12. 2019The Non-IID Data Quagmire of Decentralized Machine Learningcited by 305
27 more
  1. 2019REFUGE Challenge: A Unified Framework for Evaluating Automated Methods for Glaucoma Assessment from Fundus Photographscited by 228
  2. 2023Towards Building the Federated GPT: Federated Instruction Tuningcited by 185
  3. 2024Improving LoRA in Privacy-preserving Federated Learningcited by 161
  4. 2024FLoRA: Federated Fine-Tuning Large Language Models with Heterogeneous Low-Rank Adaptationscited by 146
  5. 2024Heterogeneous LoRA for Federated Fine-tuning of On-Device Foundation Modelscited by 116
  6. 2020PanNuke Dataset Extension, Insights and Baselinescited by 114
  7. 2024Federated Fine-tuning of Large Language Models under Heterogeneous Tasks and Client Resourcescited by 93
  8. 2024Selective Aggregation for Low-Rank Adaptation in Federated Learningcited by 80
  9. 2021HarmoFL: Harmonizing Local and Global Drifts in Federated Learning on Heterogeneous Medical Imagescited by 64
  10. 2023FATE-LLM: A Industrial Grade Federated Learning Framework for Large Language Modelscited by 63
  11. 2024Dual-Personalizing Adapter for Federated Foundation Modelscited by 55
  12. 2023Differentially Private Low-Rank Adaptation of Large Language Model Using Federated Learningcited by 41
  13. 2023pFedLoRA: Model-Heterogeneous Personalized Federated Learning with LoRA Tuningcited by 40
  14. 2024LoRA-FAIR: Federated LoRA Fine-Tuning with Aggregation and Initialization Refinementcited by 38
  15. 2025MedEyes: Learning Dynamic Visual Focus for Medical Progressive Diagnosiscited by 32
  16. 2020G1020: A Benchmark Retinal Fundus Image Dataset for Computer-Aided Glaucoma Detectioncited by 31
  17. 2025Pathology-Aware Prototype Evolution via LLM-Driven Semantic Disambiguation for Multicenter Diabetic Retinopathy Diagnosiscited by 22
  18. 2024FedFMS: Exploring Federated Foundation Models for Medical Image Segmentationcited by 21
  19. 2024Learn to Preserve and Diversify: Parameter-Efficient Group with Orthogonal Regularization for Domain Generalizationcited by 14
  20. 2025Rethinking Brain Tumor Segmentation from the Frequency Domain Perspectivecited by 9
  21. 2024RBLA: Rank-Based-LoRA-Aggregation for Fine-tuning Heterogeneous Models in FLaaScited by 8
  22. 2024SAM-Driven Weakly Supervised Nodule Segmentation with Uncertainty-Aware Cross Teachingcited by 7
  23. 2024A Federated Learning-Friendly Approach for Parameter-Efficient Fine-Tuning of SAM in 3D Segmentationcited by 5
  24. 2025Federated Client-tailored Adapter for Medical Image Segmentationcited by 3
  25. 2025Divide, Conquer and Unite: Hierarchical Style-Recalibrated Prototype Alignment for Federated Medical Segmentationcited by 3
  26. 2025FedLoRA-Optimizer: Federated LoRA Fine-Tuning with Global and Local Optimization in Heterogeneous Data Scenarioscited by 1
  27. 2026DSFedMed: Dual-Scale Federated Medical Image Segmentation via Mutual Distillation Between Foundation and Lightweight Modelscited by 1

Built on by

Not cited yet.