Cyclic Graph Attentive Match Encoder (CGAME): A Novel Neural Network For OD Estimation

TL;DR

The paper introduces CGAME, a novel neural network architecture utilizing cyclic graph attention for improved OD estimation in transportation, effectively handling cross-space inference and complex optimization challenges.

Contribution

It presents a new deep learning model with bi-directional encoding and graph matching mechanisms tailored for OD estimation, addressing limitations of existing neural architectures.

Findings

Achieves state-of-the-art performance on OD estimation tasks.

Effectively models cross-space inference with a novel graph matcher.

Demonstrates superior results compared to baseline models.

Abstract

Origin-Destination Estimation plays an important role in the era of Intelligent Transportation. Nevertheless, as a under-determined problem, OD estimation confronts many challenges from cross-space inference to non-convex, non-linear optimization. As a powerful nonlinear approximator, deep learning is an ideal data-driven method to provide a novel perspective for OD estimation. However, viewing multi-interval traffic counts as spatial-temporal inputs and OD matrix as heterogeneous graph-structured output, the existing neural network architecture is not suitable for the cross-space inference problem thus a new deep learning architecture is needed. We propose CGAME, short for cyclic graph attentive matching encoder, including bi-directional encoder-decoder networks and a novel graph matcher in the hidden layer with double-layer attention mechanism. It realizes effective information exchange between the forward networks and backward networks and establishes coupling relations across underlying feature space. The proposed model achieves state-of-the-art compared with baselines in the designed experiments and offers a paradigm for inference tasks across representation space.