paper-with-me

홈 › Papers

FUNAvg: Federated Uncertainty Weighted Averaging for Datasets with Diverse Labels

2024-07-10 · Malte Tölle, Fernando Navarro, Sebastian Eble, Ivo Wolf, Bjoern Menze, Sandy Engelhardt

Federated learning is one popular paradigm to train a joint model in a distributed, privacy-preserving environment. But partial annotations pose an obstacle meaning that categories of labels are heterogeneous over clients. We propose to learn a joint backbone in a federated manner, while each site receives its own multi-label segmentation head. By using Bayesian techniques we observe that the different segmentation heads although only trained on the individual client's labels also learn information about the other labels not present at the respective site. This information is encoded in their predictive uncertainty. To obtain a final prediction we leverage this uncertainty and perform a weighted averaging of the ensemble of distributed segmentation heads, which allows us to segment "locally unknown" structures. With our method, which we refer to as FUNAvg, we are even on-par with the models trained and tested on the same dataset on average. The code is publicly available at https://github.com/Cardio-AI/FUNAvg.

📄 PDF Abstract BibTeX arXiv:2407.07488

Code (1)

cardio-ai/funavg 공식 구현 pytorch

Tasks

Federated LearningPrivacy PreservingSegmentation

Similar Papers 제목 키워드 기반

Benchmarking federated strategies in Peer-to-Peer Federated learning for biomedical data

2024-02-15 · Jose L. Salmeron, Irina Arévalo, Antonio Ruiz-Celma

The increasing requirements for data protection and privacy has attracted a huge research interest on distributed artificial intelligence and specifically on federated learning, an emerging machine learning approach that…

BenchmarkingFederated Learning

Model Merging by Uncertainty-Based Gradient Matching

2023-10-19 · Nico Daheim, Thomas Möllenhoff, Edoardo Maria Ponti, Iryna Gurevych 외

Models trained on different datasets can be merged by a weighted-averaging of their parameters, but why does it work and when can it fail? Here, we connect the inaccuracy of weighted-averaging to mismatches in the gradie…

modelTask Arithmetic

Precision-Weighted Federated Learning

2021-07-20 · Jonatan Reyes, Lisa Di Jorio, Cecile Low-Kam, Marta Kersten-Oertel

Federated Learning using the Federated Averaging algorithm has shown great advantages for large-scale applications that rely on collaborative learning, especially when the training data is either unbalanced or inaccessib…

Computational EfficiencyFederated Learningimage-classificationImage Classification

FIVA: Federated Inverse Variance Averaging for Universal CT Segmentation with Uncertainty Estimation

2025-08-08 · Asim Ukaye, Numan Saeed, Karthik Nandakumar arxiv

Different CT segmentation datasets are typically obtained from different scanners under different capture settings and often provide segmentation labels for a limited and often disjoint set of organs. Using these heterog…

Federated Learning

WAFFLE: Weighted Averaging for Personalized Federated Learning

2021-10-13 · Martin Beaussart, Felix Grimberg, Mary-Anne Hartley, Martin Jaggi

In federated learning, model personalization can be a very effective strategy to deal with heterogeneous training data across clients. We introduce WAFFLE (Weighted Averaging For Federated LEarning), a personalized colla…

Federated LearningPersonalized Federated Learning