Summary of Federated Learning in Food Research, by Zuzanna Fendor et al.
Federated learning in food research
by Zuzanna Fendor, Bas H.M. van der Velden, Xinxin Wang, Andrea Jr. Carnoli, Osman Mutlu, Ali Hürriyetoğlu
First submitted to arxiv on: 10 Jun 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 This systematic review explores the application of federated learning in the food domain to overcome data sharing challenges. Federated learning enables training machine learning models on locally held data while only sharing learned parameters, addressing concerns around data ownership, privacy, and regulations. The study includes 41 papers that demonstrate potential applications in areas such as water quality assessment, milk quality evaluation, cybersecurity for water processing, pesticide residue risk analysis, weed detection, and fraud detection. Federated learning is predominantly applied using centralized horizontal approaches, but there remains a need to develop vertical or transfer federated learning methods and decentralized architectures. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Imagine trying to find answers to important questions in the food industry, like how to keep water clean or spot fake milk. Right now, it’s hard because different groups might not be willing to share their data due to concerns about who owns it, keeps it private, and follows certain rules. A new way to solve this problem is called federated learning. This means training computers to learn from data without sharing the actual data itself. Researchers looked at 41 papers that used this method in the food industry and found it can help with things like detecting weeds or stopping food fraud. The next step is to develop even more ways to make this work, like using different methods or making sure everyone has access. |
Keywords
» Artificial intelligence » Federated learning » Machine learning
