Summary of Federated Learning For Traffic Flow Prediction with Synthetic Data Augmentation, by Fermin Orozco et al.
Federated Learning for Traffic Flow Prediction with Synthetic Data Augmentation
by Fermin Orozco, Pedro Porto Buarque de Gusmão, Hongkai Wen, Johan Wahlström, Man Luo
First submitted to arxiv on: 11 Dec 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Distributed, Parallel, and Cluster Computing (cs.DC)
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 proposes a Federated Learning (FL) framework, FedTPS, which generates synthetic data to augment local datasets for optimal traffic flow prediction applications. The framework uses diffusion-based trajectory generation models trained through FL and leverages Temporal and Graph Attention mechanisms to learn Spatio-Temporal dependencies in regional traffic flow data. The paper evaluates the proposed framework on a large-scale ride-sharing dataset using various FL methods and Traffic Flow Prediction models, including a novel prediction model that outperforms multiple baselines. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about finding ways for cities to better predict traffic flow. Right now, each city has its own traffic data, which makes it hard for them to work together to make better predictions. The authors want to solve this problem by creating a new way for cities to share and use their data together. They propose a new framework called FedTPS that can do this. It generates fake traffic data to help cities make more accurate predictions. The authors tested this framework on real-world data from ride-sharing companies and found it worked better than other methods. |
Keywords
» Artificial intelligence » Attention » Diffusion » Federated learning » Synthetic data
