Summary of Federated Learning on Transcriptomic Data: Model Quality and Performance Trade-offs, by Anika Hannemann et al.
Federated Learning on Transcriptomic Data: Model Quality and Performance Trade-Offs
by Anika Hannemann, Jan Ewald, Leo Seeger, Erik Buchmann
First submitted to arxiv on: 22 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Cryptography and Security (cs.CR); Genomics (q-bio.GN)
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 This paper explores the application of machine learning on large-scale genomic and transcriptomic data for precision medicine, highlighting the challenges of working with sensitive, voluminous, and heterogeneous data. Federated learning is proposed as a solution to this problem, enabling decentralized machine learning without exchanging raw data. The authors conduct comparative experiments using TensorFlow Federated and Flower, training disease prognosis and cell type classification models on distributed transcriptomic data, considering both data and architectural heterogeneity. The paper evaluates model quality, robustness against privacy-enhancing noise, computational performance, and resource overhead. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Machine learning is helping doctors make better decisions about treating patients with complex diseases. One challenge is that we have a lot of genetic data, but it’s spread out across different places and can’t be easily shared because of patient privacy concerns. Federated learning is a new way to work with this data without sharing it. It lets different groups work together on the same machine learning problem without seeing each other’s raw data. This paper compares two popular federated learning tools, TensorFlow Federated and Flower, by training models to predict diseases and identify cell types. The results show that both tools can be used to build accurate models without sharing sensitive data. |
Keywords
* Artificial intelligence * Classification * Federated learning * Machine learning * Precision
