Communication-Efficient Personalized Federated Learning for Traffic Flow Prediction
Authors:
- 13 December 2024
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2173-2177
Abstract
As an important component of intelligent transportation systems, accurate traffic flow prediction can improve road traffic efficiency. Traffic data is typically represented as graphs, but data from different regions is independently collected by various organizations (clients), resulting in the division of the complete graph structure into multiple subgraphs. Feder-ated learning enables the collaborative use of these independent datasets. However, limited communication bandwidth and computational resources result in high overhead in practical scenarios, hindering the application of federated learning. To address this, we introduce an efficient pruning-based federated learning algorithm (DPruneFL), which analyzes client differences and retains personalized model parts. Additionally, we developed the FedNe-DP system by integrating this with the personalized federated learning algorithm based on neighbor aggregation (FedNe), considering both the physical relationships among subgraph data and client personalization needs during aggregation. Experimental results on real datasets show that our approach not only improves prediction performance but also reduces communication costs, enhancing the efficiency of federated learning in actual traffic flow prediction.Keywords
This publication has 11 references indexed in Scilit:
- A Hypernetwork-based Personalized Federated Learning Framework for Encrypted Traffic Classification2023
- Personalized Federated Learning with Neighbor Aggregation for Traffic Flow Prediction2023
- FedAGCN: A traffic flow prediction framework based on federated learning and Asynchronous Graph Convolutional NetworkApplied Soft Computing, 2023
- Federated optimization via knowledge codistillationExpert Systems with Applications, 2022
- Graph Transformer Attention Networks for Traffic Flow Prediction2021
- Helios: Heterogeneity-Aware Federated Learning with Dynamically Balanced Collaboration2021
- FedPrune: Personalized and Communication-Efficient Federated Learning on Non-IID Data2021
- CBFL: A Communication-Efficient Federated Learning Framework From Data Redundancy PerspectiveIEEE Systems Journal, 2021
- FASTGNN: A Topological Information Protected Federated Learning Approach for Traffic Speed ForecastingIEEE Transactions on Industrial Informatics, 2021
- A Comprehensive Survey on Graph Neural NetworksIEEE Transactions on Neural Networks and Learning Systems, 2020