Summary of Fssc: Federated Learning Of Transformer Neural Networks For Semantic Image Communication, by Yuna Yan et al.
FSSC: Federated Learning of Transformer Neural Networks for Semantic Image Communication
by Yuna Yan, Xin Zhang, Lixin Li, Wensheng Lin, Rui Li, Wenchi Cheng, Zhu Han
First submitted to arxiv on: 31 Jul 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Machine Learning (cs.LG); Image and Video Processing (eess.IV)
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 Federated Learning (FL) strategy for a Swin Transformer-based semantic communication system (FSSC) addresses image semantic communication in multi-user deployments. The paper demonstrates that using a Swin Transformer for joint source-channel coding (JSCC) effectively extracts semantic information, and then introduces an FL framework to collaboratively learn a global model without sharing clients’ data. This approach enhances user privacy protection and reduces server/mobile edge workload. Simulation evaluations show the method outperforms traditional JSCC and separate-based communication algorithms, with a Peak Signal-to-Noise Ratio (PSNR) increase of over 2dB after integrating local semantics. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper proposes a new way to send pictures across a network without compromising privacy or slowing down the server. It uses a special type of artificial intelligence called a Swin Transformer to understand what’s important in an image, and then lets multiple devices learn together without sharing their data. This makes it faster and more private than traditional methods. The results show that this new approach is better than usual and can even improve the quality of the pictures. |
Keywords
* Artificial intelligence * Federated learning * Semantics * Transformer
