Summary of Towards Resource-efficient Federated Learning in Industrial Iot For Multivariate Time Series Analysis, by Alexandros Gkillas et al.
Towards Resource-Efficient Federated Learning in Industrial IoT for Multivariate Time Series Analysis
by Alexandros Gkillas, Aris Lalos
First submitted to arxiv on: 6 Nov 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Signal Processing (eess.SP)
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 A novel federated learning framework is introduced for privacy-preserving deep anomaly detection in industrial applications, which addresses the challenges of large neural networks and user privacy concerns. By leveraging model pruning techniques at the server-side of a federated paradigm, this approach achieves high compression rates (over 99.7%) with negligible performance losses (less than 1.18%) compared to centralized solutions. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Anomaly detection in industrial applications is important but challenging because data often contains privacy concerns. To solve this problem, researchers developed deep learning models that can detect anomalies. However, these models are big and use a lot of computer power and storage space. To make it more efficient, they used a special way to train the models, called federated learning. This allows different devices to work together without sharing their data. The next step is to compress the models to reduce the amount of data being sent around, which helps with privacy and efficiency. |
Keywords
» Artificial intelligence » Anomaly detection » Deep learning » Federated learning » Pruning
