Summary of Mobility-aware Federated Self-supervised Learning in Vehicular Network, by Xueying Gu et al.
Mobility-Aware Federated Self-supervised Learning in Vehicular Network
by Xueying Gu, Qiong Wu, Pingyi Fan, Qiang Fan
First submitted to arxiv on: 1 Aug 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Networking and Internet Architecture (cs.NI)
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 paper presents Federated Learning (FL) as an advanced distributed machine learning approach that allows training models on multiple devices simultaneously without uploading all data to a roadside unit (RSU). This enables FL to handle sensitive or widely distributed data. To address labeling costs, the self-supervised learning approach is proposed, which trains models without labels. For high-velocity vehicles with blurred images, FLSimCo, an FL algorithm based on image blur level aggregation, is introduced as a pre-training stage for self-supervised learning in vehicular environments. The proposed algorithm demonstrates fast and stable convergence through simulation results. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper uses a new way of teaching machines to learn without needing labels. This is helpful when we have lots of data that keeps changing, like in cars or mobile devices. The problem is that some images can be blurry if the car is moving really fast. To solve this, the authors created an algorithm called FLSimCo that can handle blurry images and train machines quickly and accurately without needing labels. |
Keywords
» Artificial intelligence » Federated learning » Machine learning » Self supervised
