Interpretable Crowd Flow Prediction with Spatial-Temporal Self-Attention

TL;DR

This paper introduces a novel spatial-temporal self-attention network for crowd flow prediction that captures complex dependencies without dividing spatial and temporal features, improving interpretability and accuracy.

Contribution

It proposes a unified self-attention model with an encoding gate and multi-aspect attention to better model spatial-temporal dependencies in crowd flow prediction.

Findings

Reduces inflow RMSE by 16% on Taxi-NYC dataset

Reduces outflow RMSE by 8% on Taxi-NYC dataset

Improves interpretability of spatial-temporal dependencies

Abstract

Crowd flow prediction has been increasingly investigated in intelligent urban computing field as a fundamental component of urban management system. The most challenging part of predicting crowd flow is to measure the complicated spatial-temporal dependencies. A prevalent solution employed in current methods is to divide and conquer the spatial and temporal information by various architectures (e.g., CNN/GCN, LSTM). However, this strategy has two disadvantages: (1) the sophisticated dependencies are also divided and therefore partially isolated; (2) the spatial-temporal features are transformed into latent representations when passing through different architectures, making it hard to interpret the predicted crowd flow. To address these issues, we propose a Spatial-Temporal Self-Attention Network (STSAN) with an ST encoding gate that calculates the entire spatial-temporal representation with positional and time encodings and therefore avoids dividing the dependencies. Furthermore, we develop a Multi-aspect attention mechanism that applies scaled dot-product attention over spatial-temporal information and measures the attention weights that explicitly indicate the dependencies. Experimental results on traffic and mobile data demonstrate that the proposed method reduces inflow and outflow RMSE by 16% and 8% on the Taxi-NYC dataset compared to the SOTA baselines.