# FIDAL: Diversity-Aware Federated Active Learning Under Real-World Distribution Shifts

arXiv: https://arxiv.org/abs/2609.31637 · HTML: https://mlsanity.com/paper/2609.31637/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 36 of its 59 references that are in the map.
- First posted on arXiv 10 Sep 2026.

## Builds on (most cited first, 30 of 36)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds](https://mlsanity.com/paper/1906.03671/) (2019)
- [Evaluating Deep Neural Networks Trained on Clinical Images in Dermatology with the Fitzpatrick 17k Dataset](https://mlsanity.com/paper/2104.09957/) (2021)
- [Disparities in Dermatology AI: Assessments Using Diverse Clinical Images](https://mlsanity.com/paper/2111.08006/) (2021)
- [FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settings](https://mlsanity.com/paper/2210.04620/) (2022)
- [SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarios](https://mlsanity.com/paper/2107.00717/) (2021)
- [Generative Adversarial Active Learning](https://mlsanity.com/paper/1702.07956/) (2017)
- [HarmoFL: Harmonizing Local and Global Drifts in Federated Learning on Heterogeneous Medical Images](https://mlsanity.com/paper/2112.10775/) (2021)
- [A Multimodal Vision Foundation Model for Clinical Dermatology](https://mlsanity.com/paper/2410.15038/) (2024)
- [Mammo-CLIP: A Vision Language Foundation Model to Enhance Data Efficiency and Robustness in Mammography](https://mlsanity.com/paper/2405.12255/) (2024)
- [A comprehensive survey on deep active learning in medical image analysis](https://mlsanity.com/paper/2310.14230/) (2023)
- [Active Learning for Open-set Annotation](https://mlsanity.com/paper/2201.06758/) (2022)
- [Think Twice Before Selection: Federated Evidential Active Learning for Medical Image Analysis with Domain Shifts](https://mlsanity.com/paper/2312.02567/) (2023)
- [Meta-Query-Net: Resolving Purity-Informativeness Dilemma in Open-set Active Learning](https://mlsanity.com/paper/2210.07805/) (2022)
- [Entropic Open-set Active Learning](https://mlsanity.com/paper/2312.14126/) (2023)
- [Knowledge-Aware Federated Active Learning with Non-IID Data](https://mlsanity.com/paper/2211.13579/) (2022)
- [Uncertainty Herding: One Active Learning Method for All Label Budgets](https://mlsanity.com/paper/2412.20644/) (2024)
- [Federated Active Learning (F-AL): an Efficient Annotation Strategy for Federated Learning](https://mlsanity.com/paper/2202.00195/) (2022)
- [Re-thinking Federated Active Learning based on Inter-class Diversity](https://mlsanity.com/paper/2303.12317/) (2023)
- [Robust image representations with counterfactual contrastive learning](https://mlsanity.com/paper/2409.10365/) (2024)
- [Federated Learning with Uncertainty via Distilled Predictive Distributions](https://mlsanity.com/paper/2206.07562/) (2022)
- [Equipping Computational Pathology Systems with Artifact Processing Pipelines: A Showcase for Computation and Performance Trade-offs](https://mlsanity.com/paper/2403.07743/) (2024)
- [Bidirectional Uncertainty-Based Active Learning for Open Set Annotation](https://mlsanity.com/paper/2402.15198/) (2024)
- [Joint Out-of-Distribution Filtering and Data Discovery Active Learning](https://mlsanity.com/paper/2503.02491/) (2025)
- [Radio-opaque artefacts in digital mammography: automatic detection and analysis of downstream effects](https://mlsanity.com/paper/2410.03809/) (2024)
- [Deep Active Learning with Contrastive Learning Under Realistic Data Pool Assumptions](https://mlsanity.com/paper/2303.14433/) (2023)
- [Focused Active Learning for Histopathological Image Classification](https://mlsanity.com/paper/2404.04663/) (2024)

## Abstract (arXiv)

Federated learning enables collaborative model training across institutions without centralizing data, yet high annotation costs, domain shifts, and class imbalance remain major obstacles, especially when irrelevant out-of-distribution (OOD) samples dilute the labeled data. Existing active learning methods target uncertainty or diversity within in-distribution (ID) data and overlook unknown samples in federated clinical settings. We propose FIDAL, an open-set federated active learning framework that combines calibrated global-local evidential uncertainty, support-set diversity weighting, and adaptive OOD rejection. The rejection gate thresholds a foundation-model Gaussian-coverage signal per client and per round with Otsu's criterion, so that highly informative ID samples are queried while irrelevant outliers are excluded without any hand-tuned threshold. Evaluated on three multi-center medical imaging benchmarks (dermatology, histopathology, and mammography with organically occurring artifacts) in realistic open-set scenarios, FIDAL outperforms detector-based open-set methods by up to about 12 percentage points of balanced accuracy and is the only method on the accuracy-ID purity Pareto front of all three benchmarks. At an equal query budget it spends at least 1.3 times fewer annotations on OOD samples than every accuracy-matched baseline, saving an estimated 7-29 hours of expert reading on the mammography benchmark. By labeling only a fraction of the data pool, it matches or exceeds fully supervised performance across modalities. These results highlight the value of integrating uncertainty, diversity, and OOD rejection in open-set federated active learning for medicine.