Spatio-Temporal Contrastive Self-Supervised Learning for POI-level Crowd Flow Inference

TL;DR

This paper introduces a novel contrastive self-supervised learning framework, CSST, that leverages unlabeled spatio-temporal data to accurately infer crowd flow at POIs, overcoming data scarcity and complex dependencies.

Contribution

The paper proposes a new self-supervised graph representation learning method, CSST, for crowd flow inference that effectively utilizes unlabeled data and models spatio-temporal dependencies.

Findings

CSST outperforms models trained from scratch on real-world datasets.

Pre-training with noisy data enhances crowd flow inference accuracy.

The approach effectively captures complex spatio-temporal correlations.

Abstract

Accurate acquisition of crowd flow at Points of Interest (POIs) is pivotal for effective traffic management, public service, and urban planning. Despite this importance, due to the limitations of urban sensing techniques, the data quality from most sources is inadequate for monitoring crowd flow at each POI. This renders the inference of accurate crowd flow from low-quality data a critical and challenging task. The complexity is heightened by three key factors: 1) The scarcity and rarity of labeled data, 2) The intricate spatio-temporal dependencies among POIs, and 3) The myriad correlations between precise crowd flow and GPS reports. To address these challenges, we recast the crowd flow inference problem as a self-supervised attributed graph representation learning task and introduce a novel Contrastive Self-learning framework for Spatio-Temporal data (CSST). Our approach initiates with the construction of a spatial adjacency graph founded on the POIs and their respective distances. We then employ a contrastive learning technique to exploit large volumes of unlabeled spatio-temporal data. We adopt a swapped prediction approach to anticipate the representation of the target subgraph from similar instances. Following the pre-training phase, the model is fine-tuned with accurate crowd flow data. Our experiments, conducted on two real-world datasets, demonstrate that the CSST pre-trained on extensive noisy data consistently outperforms models trained from scratch.