DGCPath improves smart travel data understanding with new learning method
DGCPath: Distribution-Aware Generative Contrastive Framework for Self-supervised Path Representation Learning -- Extended Version
Artificial Intelligence
Summary
Understanding the paths vehicles take is important for smarter transportation systems. Current methods that teach computers to recognize travel patterns often struggle when used in different situations. The authors present DGCPath, a new technique that creates diverse examples of travel paths automatically and compares features in a more flexible way. This method helps computers learn better and work well across different scenarios. Tests show it performs better than older approaches on real travel data.
vehicle trajectory datapath representation learningself-supervised learningcontrastive learninggenerative modelingdiffusion modelvariational contrastive mechanismcross-view reconstructionfeature embeddingintelligent transportation systems
Authors
Sean Bin Yang, Hao Miao, Zongyi Xu, Jilin Hu, Xiangmeng Wang, Hua Lu, Bin Yang, Christian S. Jensen
Abstract
Due to the proliferation of vehicle trajectory data enabled by advanced sensing technologies, path representation learning has become a pivotal task in intelligent transportation systems. Although existing self-supervised approaches have achieved promising performance, their dependence on deterministic contrastive learning paradigms and handcrafted view augmentation strategies inherently restricts their cross-scenario generalization capabilities. To address these limitations, we present DGCPath, an innovative Distribution-aware Generative Contrastive learning framework for Path representation. This framework establishes a synergistic connection between generative modeling and distributional contrastive learning, enabling the acquisition of robust and transferable feature embeddings. Specifically, our framework incorporates: (1) a diffusion-based view generator that autonomously produces semantically coherent yet diverse trajectory views from Gaussian noise; (2) a variational contrastive mechanism that enforces latent feature alignment at the distribution level, transcending conventional instance-wise consistency; and (3) a novel generative cross-supervision module that reinforces view-level consistency through cross-view reconstruction learning. Comprehensive evaluations on three real-world trajectory datasets demonstrate that DGCPath outperforms state-of-the-art baselines on two distinct downstream tasks, validating its enhanced generalization capability and representation effectiveness.