REFINE: Trajectory Representation Learning via Closed-Loop Transcription
TL;DR
This work proposes REFINE, a simple yet effective Representation lEarning Framework that tightly couples road-network-aware generative reconstruction with feedback-driven contrastive learning, enabling the model to capture fine-grained local movement semantics and global spatio-temporal dependencies without manually designed augmentation views.
Abstract
Trajectory representation learning underpins a wide range of trajectory analytics tasks; however, most existing self-supervised approaches—whether discriminative or generative—adopt an open-loop paradigm, relying on fixed data augmentations or random masking without feedback, which limits their ability to generalize and scale. We propose REFINE, a simple yet effective Representation lEarning Framework vIa closed-loop traNscription rEfinement for trajectory data. Drawing upon feedback control theory, REFINE tightly couples road-network-aware generative reconstruction with feedback-driven contrastive learning, enabling the model to capture fine-grained local movement semantics and global spatio-temporal dependencies without manually designed augmentation views. We further provide a control-theoretic analysis that establishes convergence guarantees for the proposed closed-loop optimization. Extensive experiments on four real-world datasets offer evidence that REFINE is able to consistently outperform state-of-the-art methods across multiple downstream tasks, while being strong computationally efficient and scalable.
