Skip to content

tsinghua-fib-lab/MGRoute

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

12 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

WWW2025Industry-MRGRP

Summary

We propose a Multi-Relational Graph-based Route Prediction (MRGRP) method, which enables fine-grained modeling of the correlations among tasks influencing couriers' decision-making and achieves accurate prediction. We encode spatial and temporal proximity, along with the pickup-delivery relationships of tasks, into a multi-relational graph, then design a GraphFormer architecture to capture these complex correlations. Furthermore, we introduce a route decoder that leverages information about couriers as well as dynamic distance and time contexts for personalized prediction. It also utilizes existing route solutions as a reference to find better outcomes.

Installation

Environment

  • Tested OS: Linux
  • Python >= 3.10.0
  • PyTorch >= 1.7.0
  • hydra == 1.1

Run

python run.py --dataset_name <your_data_folder>

Performance

The metrics include KRC, LSD, ED, SR@k, HR@k, [email protected], LSD, and ED quantify the similarity between the predicted route and the ground truth from the global perspective, while SR@k, HR@k, and ACC@k measure their local similarity. Higher KRC, HR@k, ACC@k, SR@k, and lower LSD, ED indicate better performance of methods.

Hyperparameter study

We illustrate the results of hyperparameter studies as follows.

The number of MRGC layers

Task embedding sizes

Relative weight of the loss function

From the results, we find that the hyperparameter settings are:

  • # MRGC Layers: 3
  • Task embedding sizes: 256
  • Relative weight: 0.1

Diagram of multi-relational graph

The diagram of our proposed multi-relational graph is as follows.

Generation of route reference encoding

We illustrate the process of route reference encoding generation, which is employed in the decoder, as follows.

Notes

The original data is coming soon after undergoing the necessary de-identification and anonymization processes to ensure compliance with privacy regulations and ethical standards.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages