Advances in Transportation Systems and Federated Learning

The recent developments in the research area of intelligent transportation systems and federated learning have shown significant advancements in addressing critical challenges. In the domain of intelligent transportation, there is a notable focus on improving data imputation techniques for traffic data, leveraging graph structures for ridesharing optimization, and enhancing traffic crash modeling through innovative transformer-based approaches. These advancements aim to enhance the accuracy and efficiency of transportation services, contributing to better road safety and resource utilization.

In the realm of federated learning, the field is witnessing a shift towards more privacy-aware and decentralized learning paradigms. Notable innovations include the development of asynchronous federated learning frameworks that optimize for performance and cost, game-theoretic approaches for client sampling and incentive mechanisms, and the use of synthetic data augmentation to improve model performance in traffic flow prediction. These developments are crucial for enabling collaborative learning while safeguarding privacy and reducing communication overhead.

Particularly noteworthy are the frameworks that integrate game theory with federated learning to address data heterogeneity and optimize resource allocation, as well as those that leverage graph theory for ridesharing optimization, demonstrating significant improvements in efficiency and service quality. Additionally, the introduction of federated learning models for traffic flow prediction with synthetic data augmentation showcases a promising direction for handling distributed and sensitive data in transportation applications.

Sources

An Experimental Evaluation of Imputation Models for Spatial-Temporal Traffic Data

NebulaFL: Effective Asynchronous Federated Learning for JointCloud Computing

A Game-Theoretic Framework for Privacy-Aware Client Sampling in Federated Learning

StructRide: A Framework to Exploit the Structure Information of Shareability Graph in Ridesharing

PyPulse: A Python Library for Biosignal Imputation

Self-Interested Agents in Collaborative Learning: An Incentivized Adaptive Data-Centric Framework

Feature Group Tabular Transformer: A Novel Approach to Traffic Crash Modeling and Causality Analysis

Game-Theoretic Joint Incentive and Cut Layer Selection Mechanism in Split Federated Learning

Learn How to Query from Unlabeled Data Streams in Federated Learning

Federated Learning for Traffic Flow Prediction with Synthetic Data Augmentation

Data Analysis on Speeding Behavior: The Impact of Auditory Warnings and Demographic Factors

Development dilemma of ride-sharing: Revenue or social welfare?

Predicting Quality of Video Gaming Experience Using Global-Scale Telemetry Data and Federated Learning

Built with on top of