Summary of Privacy-preserving Data Fusion For Traffic State Estimation: a Vertical Federated Learning Approach, by Qiqing Wang et al.
Privacy-Preserving Data Fusion for Traffic State Estimation: A Vertical Federated Learning Approach
by Qiqing Wang, Kaidi Yang
First submitted to arxiv on: 22 Jan 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Cryptography and Security (cs.CR); Systems and Control (eess.SY)
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 paper introduces a novel vertical federated learning (FL) approach, called FedTSE, which enables multiple data owners to collaborate on traffic state estimation (TSE) without sharing their private data. This addresses the limitations of existing works that assume all data sources are accessible by a single trusted party. The method is designed for common TSE scenarios with limited availability of ground-truth data and integrates traffic models into FL, resulting in a privacy-preserving physics-informed FL approach called FedTSE-PI. Real-world data validation shows that the proposed methods can protect privacy while achieving similar accuracy to the oracle method without privacy considerations. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about making it possible for different groups to work together on estimating traffic conditions without sharing their private information. This is important because right now, each group has its own way of doing things and they don’t always have access to the same data. The researchers came up with a new way called FedTSE that lets them work together without sharing sensitive information. They also added another layer to make sure the results are accurate, which they call FedTSE-PI. It works by using traffic models to help figure out what’s going on. |
Keywords
* Artificial intelligence * Federated learning
