Full-Link Delivery Time Prediction in Logistics Using Federated Heterogeneous Graph Transformer
- 28 November 2024
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (6) , 6775-6789
Abstract
Motivated by the pursuit of greater efficiency, companies, such as Amazon and JD, are shifting toward a warehouse-distribution integration model to optimize logistics operations. In general full-link logistics scenarios, the collaboration between warehouses and sorting centers managed by different enterprises leads to data silos, posing challenges in securely sharing information and accurately predicting delivery times across the entire logistics network. Current delivery time prediction methods often overlook the heterogeneity of logistics networks and face data sharing constraints. We aim to address these issues by facilitating secure internode relationship analysis and leveraging distinct spatio-temporal characteristics to enhance efficiency. However, challenges remain in overcoming data isolation while maintaining protection and integrating diverse node characteristics for optimized modeling. To address these challenges, we propose the federated heterogeneous graph transformer (Fed-HGT) framework. This framework includes a federated training module that integrates local and central gradients by exchanging node representations and model parameters between logistics nodes and the central server. Additionally, it features a federated prediction module where local nodes compute time representations using their local data and transmit these to the central server. The central server then uses these representations to make accurate full-link delivery time predictions. Our method was evaluated on a dataset from a major e-commerce platform in China, demonstrating significant performance improvements over existing solutions.Keywords
Funding Information
- Science and Technology Innovation 2030 (2021ZD0114202)
This publication has 28 references indexed in Scilit:
- SPADE: GPU-Powered Spatial Database Engine for Commodity Hardware2022
- Cluster-driven Graph Federated Learning over Multiple Domains2021
- FASTGNN: A Topological Information Protected Federated Learning Approach for Traffic Speed ForecastingIEEE Transactions on Industrial Informatics, 2021
- AMBD: Attention Based Multi-Block Deep Learning Model for Warehouse Dwell Time Prediction2021
- LCFI: A Fault Injection Tool for Studying Lossy Compression Error Propagation in HPC Programs2020
- An estimation distribution algorithm for wave-picking warehouse managementJournal of Intelligent Manufacturing, 2020
- Quantitative approaches for the integration of production and distribution planning in the supply chain: a systematic literature reviewInternational Journal of Production Research, 2020
- Modeling Relational Data with Graph Convolutional Networks2018
- Deep learningNature, 2015
- Travel time estimation and order batching in a 2-block warehouseEuropean Journal of Operational Research, 2007