Hybrid Graph Embedding Techniques in Estimated Time of Arrival Task

TL;DR

This paper explores advanced graph embedding techniques for improving ETA prediction accuracy, focusing on generalization in sparse and temporally variable road networks using a novel two-stage approach.

Contribution

It introduces a two-stage method that enhances graph embedding generalization for ETA tasks, addressing data sparsity and temporal variability issues.

Findings

Improved ETA prediction accuracy over baseline models

Enhanced generalization in sparse road network data

Effective handling of temporal variations in travel conditions

Abstract

Recently, deep learning has achieved promising results in the calculation of Estimated Time of Arrival (ETA), which is considered as predicting the travel time from the start point to a certain place along a given path. ETA plays an essential role in intelligent taxi services or automotive navigation systems. A common practice is to use embedding vectors to represent the elements of a road network, such as road segments and crossroads. Road elements have their own attributes like length, presence of crosswalks, lanes number, etc. However, many links in the road network are traversed by too few floating cars even in large ride-hailing platforms and affected by the wide range of temporal events. As the primary goal of the research, we explore the generalization ability of different spatial embedding strategies and propose a two-stage approach to deal with such problems.