# Micro-Macro Spatial-Temporal Graph-based Encoder-Decoder for Map-Constrained Trajectory Recovery

arXiv: https://arxiv.org/abs/2404.19141 · HTML: https://mlsanity.com/paper/2404.19141/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 49 references that are in the map.
- First posted on arXiv 29 Apr 2024.

## Builds on (most cited first, 11 of 11)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [ETA Prediction with Graph Neural Networks in Google Maps](https://mlsanity.com/paper/2108.11482/) (2021)
- [Self-supervised Trajectory Representation Learning with Temporal Regularities and Travel Semantics](https://mlsanity.com/paper/2211.09510/) (2022)
- [Deep Spatially and Temporally Aware Similarity Computation for Road Network Constrained Trajectories](https://mlsanity.com/paper/2112.09339/) (2021)
- [Generating Long-term Trajectories Using Deep Hierarchical Networks](https://mlsanity.com/paper/1706.07138/) (2017)
- [RNTrajRec: Road Network Enhanced Trajectory Recovery with Spatial-Temporal Transformer](https://mlsanity.com/paper/2211.13234/) (2022)
- [AttnMove: History Enhanced Trajectory Recovery via Attentional Network](https://mlsanity.com/paper/2101.00646/) (2021)
- [A Force-Directed Approach for Offline GPS Trajectory Map Matching](https://mlsanity.com/paper/1903.12400/) (2019)

## Built on by (most cited first, 9 of 9)

- [Sports-Traj: A Unified Trajectory Generation Model for Multi-Agent Movement in Sports](https://mlsanity.com/paper/2405.17680/) (2024)
- [TrajFM: A Vehicle Trajectory Foundation Model for Region and Task Transferability](https://mlsanity.com/paper/2408.15251/) (2024)
- [TransferTraj: A Vehicle Trajectory Learning Model for Region and Task Transferability](https://mlsanity.com/paper/2505.12672/) (2025)
- [Learning Spatio-Temporal Dynamics for Trajectory Recovery via Time-Aware Transformer](https://mlsanity.com/paper/2505.13857/) (2025)
- [PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents](https://mlsanity.com/paper/2605.10341/) (2026)
- [PLMTrajRec: A Scalable and Generalizable Trajectory Recovery Method with Pre-trained Language Models](https://mlsanity.com/paper/2410.14281/) (2024)
- [ProDiff: Prototype-Guided Diffusion for Minimal Information Trajectory Imputation](https://mlsanity.com/paper/2505.23048/) (2025)
- [Efficient Methods for Accurate Sparse Trajectory Recovery and Map Matching](https://mlsanity.com/paper/2508.10460/) (2025)
- [UM3: Unsupervised Map to Map Matching](https://mlsanity.com/paper/2508.16874/) (2025)

## Abstract (arXiv)

Recovering intermediate missing GPS points in a sparse trajectory, while adhering to the constraints of the road network, could offer deep insights into users' moving behaviors in intelligent transportation systems. Although recent studies have demonstrated the advantages of achieving map-constrained trajectory recovery via an end-to-end manner, they still face two significant challenges. Firstly, existing methods are mostly sequence-based models. It is extremely hard for them to comprehensively capture the micro-semantics of individual trajectory, including the information of each GPS point and the movement between two GPS points. Secondly, existing approaches ignore the impact of the macro-semantics, i.e., the road conditions and the people's shared travel preferences reflected by a group of trajectories. To address the above challenges, we propose a Micro-Macro Spatial-Temporal Graph-based Encoder-Decoder (MM-STGED). Specifically, we model each trajectory as a graph to efficiently describe the micro-semantics of trajectory and design a novel message-passing mechanism to learn trajectory representations. Additionally, we extract the macro-semantics of trajectories and further incorporate them into a well-designed graph-based decoder to guide trajectory recovery. Extensive experiments conducted on sparse trajectories with three different sampling intervals that are respectively constructed from two real-world trajectory datasets demonstrate the superiority of our proposed model.