Full-Link Delivery Time Prediction in Logistics Using Federated Heterogeneous Graph Transformer

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.

I. Introduction

Driven by the need for greater efficiency and streamlined operations, companies like Amazon [1], Taobao [2], and JD [3] are transitioning to a warehouse-distribution integration model [4]. This approach integrates sales, warehousing, and distribution within a single entity, is further enhanced by Internet of Things (IoT) devices collecting vast amounts of information, optimizing logistics and enhancing service quality. However, in general full-link logistics scenarios, multiple logistics enterprises manage warehouses and sorting centers, requiring collaboration while ensuring data security and effectively utilizing heterogeneous spatio-temporal data. Due to strict data protection requirements, spatio-temporal data is not directly transmitted to the central server. Instead, node representations, model parameters, and gradient data are exchanged for training purposes. Our research focuses on accurately estimating full-link delivery times within this scenarios.