Spatial Temporal Representation Learning and POI-Rec

A paper list for ST-based represenation learning and POI recommenation.

Must-read Papers on Spatial Temporal Representation Learning

Mainly Contributed and Maintained by Chengyin Li and Yao Qiang.

Thanks for all great contributors on GitHub!

Contents

• Papers
• Preprints
• Some Applications
• Acknowledgements

Papers

1. Pre-training Context and Time Aware Location Embeddings from Spatial-Temporal Trajectories for User Next Location Prediction. Lin, Yan, Huaiyu Wan, Shengna Guo and Youfang Lin. AAAI (2021).[pdf]
2. Urban2Vec: Incorporating Street View Imagery and POIs for Multi-Modal Urban Neighborhood Embedding. Wang, Zhecheng, Haoyuan Li and R. Rajagopal. AAAI (2020). [pdf]
3. Multi-View Joint Graph Representation Learning for Urban Region Embedding. Zhang, Mingyang, Tong Li, Y. Li and Pan Hui. IJCAI (2020). [pdf] [code]
4. Exploiting Mutual Information for Substructure-aware Graph Representation Learning. Wang, Pengyang, Yanjie Fu, Yuanchun Zhou, Kunpeng Liu, Xiaolin Li and K. Hua. IJCAI (2020). [pdf]
5. Leveraging an Efficient and Semantic Location Embedding to Seek New Ports of Bike Share Services. Wang, Yuan, Chenwei Wang, Yinan Ling, Keita Yokoyama, Hsin-Tai Wu and Yi Fang. IEEE Big Data (2020). [pdf]
6. Tree Structure-Aware Graph Representation Learning via Integrated Hierarchical Aggregation and Relational Metric Learning. Qiao, Ziyue, Pengyang Wang, Yanjie Fu, Yi Du, P. Wang and Yuanchun Zhou. ICDM (2020). [pdf] [code]
7. Heterogeneous Dynamic Graph Attention Network. Li, Qiuyan, Yanlei Shang, Xiuquan Qiao and Wei Dai. ICKG, 2020. [pdf] [code]
8. Heterogeneous Graph Attention Network. Xiao, Wang and Houye, Ji and Chuan, Shi and Bai, Wang and Peng, Cui and P. , Yu and Yanfang, Ye. WWW (2019). [pdf] [code]
9. Beyond Geo-First Law: Learning Spatial Representations via Integrated Autocorrelations and Complementarity. Du, Jiadi, Yunchao Zhang, Pengyang Wang, J. Leopold and Yanjie Fu. ICDM (2019). [pdf]
10. Unifying Inter-region Autocorrelation and Intra-region Structures for Spatial Embedding via Collective Adversarial Learning. Zhang, Yunchao, Yanjie Fu, Pengyang Wang, Xiaolin Li and Y. Zheng. KDD (2019). [pdf]
11. Unsupervised Representation Learning of Spatial Data via Multimodal Embedding. Jenkins, P., A. Farag, Suhang Wang and Z. Li. CIKM 2019. [pdf] [code]
12. Efficient Region Embedding with Multi-View Spatial Networks: A Perspective of Locality-Constrained Spatial Autocorrelations. Fu, Yanjie, Pengyang Wang, Jiadi Du, Le Wu and Xiaolin Li. AAAI (2019). [pdf]
13. Tile2Vec: Unsupervised representation learning for spatially distributed data. Jean, Neal, Sherrie Wang, Anshul Samar, G. Azzari, D. Lobell and S. Ermon. AAAI (2018). [pdf] [code]
14. Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2vec. Qiu, J., Yuxiao Dong, Hao Ma, J. Li, Kuansan Wang and Jie Tang. WSDM (2018). [pdf] [code]
15. Representing urban functions through zone embedding with human mobility patterns. Yao, Zijun, Yanjie Fu, Bin Liu, Wangsu Hu, and Hui Xiong. IJCAI (2018). [pdf]
16. DeepMove: Predicting Human Mobility with Attentional Recurrent Networks Jie Feng, Yong Li, Chao Zhang, Funing Sun, Fanchao Meng, Ang Guo, Depeng Jin WWW(2018)[pdf]
17. Region representation learning via mobility flow. Wang, Hongjian, and Zhenhui Li. CIKM (2017). [pdf]
18. POI2Vec: Geographical Latent Representation for Predicting Future Visitors. Shanshan Feng, Gao Cong, Bo An, Yeow Meng Chee. AAAI (2017).[pdf]
19. Max-Margin DeepWalk: Discriminative Learning of Network Representation. Tu, Cunchao, Weichen Zhang, Zhiyuan Liu and Maosong Sun. IJCAI (2016). [pdf] [code]
20. DeepWalk: online learning of social representations. Perozzi, Bryan, Rami Al-Rfou and S. Skiena. KDD (2014). [pdf] [code]
21. Discovering Urban Functional Zones Using Latent Activity Trajectories Nicholas Jing Yuan, et al., KDD (2012). [pdf]

Preprints

1. Modelling Urban Dynamics with Multi-Modal Graph Convolutional Networks. D'Silva, Krittika, Jordan Cambe, A. Noulas, C. Mascolo and Adam Waksman. ArXiv (2021). [pdf]
2. Learning Neighborhood Representation from Multi-Modal Multi-Graph: Image, Text, Mobility Graph and Beyond. Huang, Tianyuan, Zhecheng Wang, Hao Sheng, Andrew Ng and R. Rajagopal. ArXiv (2021). [pdf]
3. Variational graph auto-encoders. Kipf, Thomas N., and Max Welling. ArXiv (2016). [pdf] [code]

Some Applications

1. GSNet: Learning Spatial-Temporal Correlations from Geographical and Semantic Aspects for Traffic Accident Risk Forecasting. Wang, Beibei, Youfang Lin, Shengnan Guo, and Huaiyu Wan. AAAI (2021). [pdf] [code]
2. Spatial-temporal synchronous graph convolutional networks: A new framework for spatial-temporal network data forecasting. Song, Chao, Youfang Lin, Shengnan Guo, and Huaiyu Wan. AAAI (2020). [pdf] [code]

Related Papers for Point Of Interest (POI) Recommenations

Research Papers

1. [2021 IJCAI] MFNP: A Meta-optimized Model for Few-shot Next POI Recommendation. [pdf]
2. [2021 AAAI] Pre-training Context and Time Aware Location Embeddings from Spatial-Temporal Trajectories for User Next Location Prediction. [pdf]
3. [2021 WWW] STAN: Spatio-Temporal Attention Network for Next Location Recommendation. [pdf] [code]
4. [2021 WWW] Incremental Spatio-Temporal Graph Learning for Online Query-POI Matching. [pdf]
5. [2020 IJCAI] Why We Go Where We Go: Profiling User Decisions on Choosing POIs. [pdf]
6. [2020 IJCAI] Geo-ALM: POI Recommendation by Fusing Geographical Information and Adversarial Learning Mechanism. [pdf]
7. [2020 IJCAI] Discovering Subsequence Patterns for Next POI Recommendation. [pdf]
8. [2020 IJCAI] An Interactive Multi-Task Learning Framework for Next POI Recommendation with Uncertain Check-ins. [pdf]
9. [2020 TKDE] Where to go next: A spatio-temporal gated network for next poi recommendation." [pdf]
10. [2020 AAAI] Where to go next: Modeling long-and short-term user preferences for point-of-interest recommendation. [pdf]
11. [2020 WWW] Next point-of-interest recommendation on resource-constrained mobile devices. [pdf]
12. [2019 AAAI] Modelling of bi-directional spatio-temporal dependence and users’ dynamic preferences for missing poi check-in identification. [pdf]
13. [2019 KDD] Topic-enhanced memory networks for personalised point-of-interest recommendation. [pdf]
14. [2019 IJCAI] Graph Contextualized Self-Attention Network for Session-based Recommendation. [pdf]
15. [2019 SIGIR] Category-aware location embedding for point-of-interest recommendation. [pdf]

Survey Papers

• [2020] A Survey on Deep Learning Based Point-Of-Interest (POI) Recommendations. [pdf]
• [2020] A Survey on Point-of-Interest Recommendation in Location-based Social Networks. [pdf]

Datasets

• Gowalla [link]
• Foursquare [link]
• Brightkite [link]

Acknowledgements

We will continue to update this paper list. If you have any suggestions, you can add an issue.

Great thanks to other contributors ! (names are not listed in particular order)

Please contact us if we miss your names in this list, we will add you back ASAP!