Graph Masked Autoencoder for Spatio-Temporal Graph Learning
Authors:
- Qianru ZhangQZQianru Zhang
- Haixin WangHWHaixin Wang
- Siu-Ming YiuSYSiu-Ming Yiu
- Hongzhi YinHYHongzhi Yin
Preprint
Abstract
Effective spatio-temporal prediction frameworks play a crucial role in urban sensing applications, including traffic analysis, human mobility behavior modeling, and citywide crime prediction. However, the presence of data noise and label sparsity in spatio-temporal data presents significant challenges for existing neural network models in learning effective and robust region representations. To address these challenges, we propose a novel spatio-temporal graph masked autoencoder paradigm that explores generative self-supervised learning for effective spatio-temporal data augmentation. Our proposed framework introduces a spatial-temporal heterogeneous graph neural encoder that captures region-wise dependencies from heterogeneous data sources, enabling the modeling of diverse spatial dependencies. In our spatio-temporal self-supervised learning paradigm, we incorporate a masked autoencoding mechanism on node representations and structures. This mechanism automatically distills heterogeneous spatio-temporal dependencies across regions over time, enhancing the learning process of dynamic region-wise spatial correlations. To validate the effectiveness of our STGMAE framework, we conduct extensive experiments on various spatio-temporal mining tasks. We compare our approach against state-of-the-art baselines. The results of these evaluations demonstrate the superiority of our proposed framework in terms of performance and its ability to address the challenges of spatial and temporal data noise and sparsity in practical urban sensing scenarios.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- Spatio-Temporal Graph Neural Networks for Predictive Learning in Urban Computing: A SurveyIEEE Transactions on Knowledge and Data Engineering, 2023
- Modeling, Replicating, and Predicting Human Behavior: A SurveyACM Transactions on Autonomous and Adaptive Systems, 2023
- Adaptive Spatio-temporal Graph Neural Network for traffic forecastingKnowledge-Based Systems, 2022
- Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow ForecastingProceedings of the AAAI Conference on Artificial Intelligence, 2021
- Graph Attention Auto-Encoders2020
- Category-Aware Location Embedding for Point-of-Interest Recommendation2019
- Unifying Inter-region Autocorrelation and Intra-region Structures for Spatial Embedding via Collective Adversarial Learning2019
- Efficient Region Embedding with Multi-View Spatial Networks: A Perspective of Locality-Constrained Spatial AutocorrelationsProceedings of the AAAI Conference on Artificial Intelligence, 2019
- Region Representation Learning via Mobility Flow2017
- From n-gram to skipgram to concgramCorpus Studies of Language Through Time, 2006