# FedHisto-PAST: Parameter-Efficient Stain-Aware Federated Learning for Cross-Site Lung Histopathology Classification

arXiv: https://arxiv.org/abs/2609.31150 · HTML: https://mlsanity.com/paper/2609.31150/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 42 references that are in the map.
- First posted on arXiv 25 Sep 2026.

## Builds on (most cited first, 21 of 21)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [FedBN: Federated Learning on Non-IID Features via Local Batch Normalization](https://mlsanity.com/paper/2102.07623/) (2021)
- [FedProto: Federated Prototype Learning across Heterogeneous Clients](https://mlsanity.com/paper/2105.00243/) (2021)
- [Multimodal Whole Slide Foundation Model for Pathology](https://mlsanity.com/paper/2411.19666/) (2024)
- [Siloed Federated Learning for Multi-Centric Histopathology Datasets](https://mlsanity.com/paper/2008.07424/) (2020)
- [Hibou: A Family of Foundational Vision Transformers for Pathology](https://mlsanity.com/paper/2406.05074/) (2024)
- [Federated Learning for Computational Pathology on Gigapixel Whole Slide Images](https://mlsanity.com/paper/2009.10190/) (2020)
- [Benchmarking foundation models as feature extractors for weakly-supervised computational pathology](https://mlsanity.com/paper/2408.15823/) (2024)
- [WSSS4LUAD: Grand Challenge on Weakly-supervised Tissue Semantic Segmentation for Lung Adenocarcinoma](https://mlsanity.com/paper/2204.06455/) (2022)
- [Nuclei instance segmentation and classification in histopathology images with StarDist](https://mlsanity.com/paper/2203.02284/) (2022)
- [Federated Stain Normalization for Computational Pathology](https://mlsanity.com/paper/2209.14849/) (2022)
- [HistoViT: Vision Transformer for Accurate and Scalable Histopathological Cancer Diagnosis](https://mlsanity.com/paper/2508.11181/) (2025)
- [FedSODA: Federated Cross-assessment and Dynamic Aggregation for Histopathology Segmentation](https://mlsanity.com/paper/2312.12824/) (2023)
- [FMDNN: A Fuzzy-guided Multi-granular Deep Neural Network for Histopathological Image Classification](https://mlsanity.com/paper/2407.15312/) (2024)
- [FedDP: Privacy-preserving method based on federated learning for histopathology image segmentation](https://mlsanity.com/paper/2411.04509/) (2024)
- [FedWSIDD: Federated Whole Slide Image Classification via Dataset Distillation](https://mlsanity.com/paper/2506.15365/) (2025)
- [FedSDA: Federated Stain Distribution Alignment for Non-IID Histopathological Image Classification](https://mlsanity.com/paper/2511.12044/) (2025)
- [FedStain: Modeling Higher-Order Stain Statistics for Federated Domain Generalization in Computational Pathology](https://mlsanity.com/paper/2605.14590/) (2026)

## Abstract (arXiv)

Cross-site lung histopathology classification must account for stain variation, non-IID client data, missing classes, and the cost of adapting large pathology encoders. This study evaluates FedHisto-PAST v2 for three-way classification of adenocarcinoma (ACA), Normal, and squamous cell carcinoma (SCC). FedHisto-PAST v2 combines a frozen HIBOU-B foundation model with parameter-efficient adaptation, stain-conditioned paired-view prediction and feature consistency, reliability-aware prototype learning, and adaptive federated aggregation. Experiments used a five-client, non-IID, raw-data-local simulation with fixed internal evaluation, client-level analysis, component ablations, communication accounting, and a development-influenced exploratory LungHist700 cohort. All principal methods achieved near- ceiling internal performance, which limited discrimination on the fixed split. On LungHist700, FedHisto- PAST v2 achieved a Macro-F1 of 0.728560 and a balanced accuracy of 0.730454. Higher recognition of Normal and SCC was accompanied by lower ACA recall, and calibration remained imperfect. Prediction-level consistency was the only component with a clearly supported independent contribution in the external ablation analysis. Feature consistency and prototype regularization showed no conclusive independent overall gains in Macro-F1. The framework updated 1.253841% of the model parameters. The results provide exploratory cross-dataset evidence for stain-aware, parameter-efficient federation; they do not establish formal privacy, patient-level independence, prospective deployment, or clinical validation.