Summary of Residual-inr: Communication Efficient On-device Learning Using Implicit Neural Representation, by Hanqiu Chen et al.
Residual-INR: Communication Efficient On-Device Learning Using Implicit Neural Representation
by Hanqiu Chen, Xuebin Yao, Pradeep Subedi, Cong Hao
First submitted to arxiv on: 10 Aug 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Distributed, Parallel, and Cluster Computing (cs.DC); 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 Residual-INR framework is a fog computing-based communication-efficient on-device learning approach that utilizes implicit neural representation (INR) to compress images/videos into neural network weights. This technique enhances data transfer efficiency by collecting JPEG images from edge devices, compressing them into INR format at the fog node, and redistributing them for on-device learning. The framework achieves up to 5.16x reduction in data transmission across a network of 10 edge devices and facilitates CPU-free accelerated on-device learning with up to 2.9x speedup without sacrificing accuracy. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Residual-INR is a new way to make computers learn together quickly and efficiently. It’s like having a special kind of internet that lets devices share information and work together better. This makes it faster and more accurate for devices to learn from each other. The technique is especially useful when many devices need to communicate with each other, which can slow things down. |
Keywords
» Artificial intelligence » Neural network
