Link Representation Learning for Probabilistic Travel Time Estimation

TL;DR

This paper introduces ProbETA, a deep hierarchical probabilistic model that captures trip correlations for more accurate travel time estimation, outperforming existing methods on real GPS datasets.

Contribution

The paper proposes a novel joint probabilistic model for travel time estimation that accounts for inter-trip correlations and introduces a data augmentation technique for learning link representations.

Findings

ProbETA reduces MAPE by over 12.60% compared to baselines.

Learned link representations align with network geometry.

Model effectively captures trip correlations in real-world data.

Abstract

Travel time estimation is a key task in navigation apps and web mapping services. Existing deterministic and probabilistic methods, based on the assumption of trip independence, predominantly focus on modeling individual trips while overlooking trip correlations. However, real-world conditions frequently introduce strong correlations between trips, influenced by external and internal factors such as weather and the tendencies of drivers. To address this, we propose a deep hierarchical joint probabilistic model ProbETA for travel time estimation, capturing both inter-trip and intra-trip correlations. The joint distribution of travel times across multiple trips is modeled as a low-rank multivariate Gaussian, parameterized by learnable link representations estimated using the empirical Bayes approach. We also introduce a data augmentation method based on trip sub-sampling, allowing for fine-grained gradient backpropagation when learning link representations. During inference, our model estimates the probability distribution of travel time for a queried trip, conditional on spatiotemporally adjacent completed trips. Evaluation on two real-world GPS trajectory datasets demonstrates that ProbETA outperforms state-of-the-art deterministic and probabilistic baselines, with Mean Absolute Percentage Error decreasing by over 12.60%. Moreover, the learned link representations align with the physical network geometry, potentially making them applicable for other tasks.