Summary of A Cautionary Tale on the Cost-effectiveness Of Collaborative Ai in Real-world Medical Applications, by Francesco Cremonesi et al.
A cautionary tale on the cost-effectiveness of collaborative AI in real-world medical applications
by Francesco Cremonesi, Lucia Innocenti, Sebastien Ourselin, Vicky Goh, Michela Antonelli, Marco Lorenzi
First submitted to arxiv on: 9 Dec 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed benchmark compares the accuracy and cost-effectiveness of federated learning (FL) and consensus-based learning (CBL) methods in various medical data analysis scenarios. The study includes 7 datasets, 3 tasks, 8 modalities, and multi-centric settings involving 2-23 clients. The results show that CBL is a cost-effective alternative to FL, offering equivalent accuracy while reducing training time and communication costs by up to 15-fold and 60-fold, respectively. This study highlights the potential for CBL in real-world applications, particularly in terms of sustainability and democratisation of AI. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper compares different machine learning methods called Federated Learning (FL) and Consensus-Based Learning (CBL). They tested these methods on medical data to see which one works best. The study used 7 datasets, did 3 types of tasks, and looked at 8 ways of gathering data. They also simulated different scenarios where multiple teams worked together. The results show that CBL is a good alternative to FL because it’s faster and cheaper. This can help make artificial intelligence more accessible to people. |
Keywords
» Artificial intelligence » Federated learning » Machine learning
