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

arXiv: https://arxiv.org/abs/2111.14625 · HTML: https://mlsanity.com/paper/2111.14625/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 69 references that are in the map.
- First posted on arXiv 26 Nov 2021.

## Builds on (most cited first, 13 of 13)

- [T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Prediction](https://mlsanity.com/paper/1811.05320/) (2018)
- [MolGAN: An implicit generative model for small molecular graphs](https://mlsanity.com/paper/1805.11973/) (2018)
- [Efficient Graph Generation with Graph Recurrent Attention Networks](https://mlsanity.com/paper/1910.00760/) (2019)
- [NetGAN: Generating Graphs via Random Walks](https://mlsanity.com/paper/1803.00816/) (2018)
- [GraphGAN: Graph Representation Learning with Generative Adversarial Nets](https://mlsanity.com/paper/1711.08267/) (2017)
- [SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networks](https://mlsanity.com/paper/2102.05034/) (2021)
- [Deep Coordination Graphs](https://mlsanity.com/paper/1910.00091/) (2019)
- [Learning Phase Competition for Traffic Signal Control](https://mlsanity.com/paper/1905.04722/) (2019)
- [Learning Graph Embedding with Adversarial Training Methods](https://mlsanity.com/paper/1901.01250/) (2019)
- [GCN-GAN: A Non-linear Temporal Link Prediction Model for Weighted Dynamic Networks](https://mlsanity.com/paper/1901.09165/) (2019)
- [Contextualized Spatial-Temporal Network for Taxi Origin-Destination Demand Prediction](https://mlsanity.com/paper/1905.06335/) (2019)
- [Estimating multi-class dynamic origin-destination demand through a forward-backward algorithm on computational graphs](https://mlsanity.com/paper/1903.04681/) (2019)
- [DeepGG: a Deep Graph Generator](https://mlsanity.com/paper/2006.04159/) (2020)

## Abstract (arXiv)

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.