Link Representation Learning for Probabilistic Travel Time Estimation
This work addresses travel time estimation for navigation apps and web mapping services by introducing a novel probabilistic model that accounts for trip correlations, representing an incremental improvement over existing methods.
The paper tackles the problem of travel time estimation by addressing the overlooked correlations between trips, proposing a deep hierarchical joint probabilistic model called ProbETA that captures both inter-trip and intra-trip correlations, resulting in a Mean Absolute Percentage Error decrease of over 12.60% compared to state-of-the-art baselines.
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.