mlsanityData to 14 Oct 2026

A cautionary tale on the cost-effectiveness of collaborative AI in real-world medical applications

arXiv 2412.06494 ↗First posted 9 Dec 2024cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) has gained wide popularity as a collaborative learning paradigm allowing collaborative Artificial Intelligence (AI) in sensitive healthcare applications. Nevertheless, the practical implementation of FL presents technical and organizational challenges, as it generally requires complex communication infrastructures. In this context, consensus-based learning (CBL) may represent a promising alternative for collaborative learning, allowing the combination of local knowledge into a federated decision system, while potentially reducing deployment overhead. Nevertheless, a comprehensive assessment of the viability of consensus-based learning as a cost-effective and sustainable alternative to federated learning has not yet been conducted. In this work we propose an extensive benchmark of the accuracy, cost-effectiveness, and sustainability of a panel of FL and CBL methods in a wide range of collaborative medical data analysis scenarios. The benchmark includes 7 different medical datasets, encompassing 3 machine learning tasks, 8 different data modalities, and multi-centric settings involving 3 to 23 clients. Our results reveal that CBL is a cost-effective and more sustainable alternative to FL. When compared across the panel of medical datasets in the considered benchmark, CBL methods provide equivalent accuracy to the one achieved by FL. Nonetheless, CBL significantly reduces training time and communication cost (resp. 15 fold and 131 fold decrease) (p-value < 0.05). This study opens a novel perspective on the deployment of collaborative AI in real-world applications, whereas the adoption of cost-effective methods is instrumental to achieve sustainability and democratization of AI by alleviating the need for extensive computational resources.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 42 of its 106 references that are in the map. First posted on arXiv 9 Dec 2024.

Builds on

42 of 106 references.

References · 42

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  5. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  6. 2019Advances and Open Problems in Federated Learningcited by 3,046
  7. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  8. 2020Adaptive Federated Optimizationcited by 1,046
  9. 2018LEAF: A Benchmark for Federated Settingscited by 792
  10. 2020The Future of Digital Health with Federated Learningcited by 633
  11. 2021The Medical Segmentation Decathloncited by 628
  12. 2020Federated Learning with Matched Averagingcited by 564
30 more
  1. 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 536
  2. 2022MONAI: An open-source framework for deep learning in healthcarecited by 448
  3. 20183D MRI brain tumor segmentation using autoencoder regularizationcited by 328
  4. 2019Robust Aggregation for Federated Learningcited by 317
  5. 2021Ensemble deep learning: A reviewcited by 284
  6. 2016Skin Lesion Analysis toward Melanoma Detection: A Challenge at the International Symposium on Biomedical Imaging (ISBI) 2016, hosted by the International Skin Imaging Collaboration (ISIC)cited by 198
  7. 2021Federated Learning with Buffered Asynchronous Aggregationcited by 190
  8. 2020TorchIO: A Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learningcited by 177
  9. 2019The KiTS19 Challenge Data: 300 Kidney Tumor Cases with Clinical Context, CT Semantic Segmentations, and Surgical Outcomescited by 172
  10. 2020CheXclusion: Fairness gaps in deep chest X-ray classifierscited by 153
  11. 2017PMLB: A Large Benchmark Suite for Machine Learning Evaluation and Comparisoncited by 140
  12. 2021FedScale: Benchmarking Model and System Performance of Federated Learning at Scalecited by 136
  13. 2019One-Shot Federated Learningcited by 125
  14. 2022FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settingscited by 125
  15. 2022Federated Learning Enables Big Data for Rare Cancer Boundary Detectioncited by 84
  16. 2018An Empirical Study of Rich Subgroup Fairness for Machine Learningcited by 81
  17. 2021The Federated Tumor Segmentation (FeTS) Challengecited by 50
  18. 2022pFL-Bench: A Comprehensive Benchmark for Personalized Federated Learningcited by 44
  19. 2021FLOP: Federated Learning on Medical Datasets using Partial Networkscited by 42
  20. 2021HiRID-ICU-Benchmark -- A Comprehensive Machine Learning Benchmark on High-resolution ICU Datacited by 39
  21. 2022Federated Learning for Healthcare Domain - Pipeline, Applications and Challengescited by 34
  22. 2020Fed-Focal Loss for imbalanced data classification in Federated Learningcited by 26
  23. 2023Fed-BioMed: Open, Transparent and Trusted Federated Learning for Real-world Healthcare Applicationscited by 10
  24. 2020Evaluating the Communication Efficiency in Federated Learning Algorithmscited by 9
  25. 2022An Analysis on Ensemble Learning optimized Medical Image Classification with Deep Convolutional Neural Networkscited by 8
  26. 2022SafeNet: The Unreasonable Effectiveness of Ensembles in Private Collaborative Learningcited by 5
  27. 2021Fairness-Driven Private Collaborative Machine Learningcited by 4
  28. 2024Benchmarking federated strategies in Peer-to-Peer Federated learning for biomedical datacited by 3
  29. 2023Benchmarking Collaborative Learning Methods Cost-Effectiveness for Prostate Segmentationcited by 2
  30. 2021The More, the Better? A Study on Collaborative Machine Learning for DGA Detectioncited by 1

Built on by

Not cited yet.