Summary of Energy-efficient Edge Learning Via Joint Data Deepening-and-prefetching, by Sujin Kook et al.
Energy-Efficient Edge Learning via Joint Data Deepening-and-Prefetching
by Sujin Kook, Won-Yong Shin, Seong-Lyun Kim, Seung-Woo Ko
First submitted to arxiv on: 19 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Information Theory (cs.IT)
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 joint data deepening-and-prefetching (JD2P) architecture is designed to optimize data offloading from IoT devices to edge servers. This approach leverages two key techniques: data deepening, which prioritizes feature transmission based on importance determined by PCA; and data prefetching, which proactively transmits features likely needed in the future. The goal is to reduce energy consumption while maintaining accurate learning accuracy. Experiments using the MNIST dataset demonstrate the effectiveness of JD2P in reducing expected energy consumption compared to benchmarks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper proposes a new way for IoT devices to send data to edge servers. Right now, this process is slow and uses too much energy because it sends all the data at once. The authors came up with an idea called JD2P that breaks down the data into smaller pieces and sends them separately. This helps reduce the amount of energy used while still keeping the information accurate. They tested this method using a popular dataset and found it worked well. |
Keywords
* Artificial intelligence * Pca
