Yan Luo
Skip Abstract Section
Abstract
Cities are very complex systems. Representing urban regions are essential for exploring, understanding, and predicting properties and features of cities. The enrichment of multi-modal urban big data has provided opportunities for researchers to enhance urban region embedding. However, existing works failed to develop an integrated pipeline that fully utilizes effective and informative data sources within geographic units. In this article, we regard a geo-tile as a geographic unit and propose a multi-modal and multi-stage representation learning framework, namely Geo-Tile2Vec, for urban analytics, especially for urban region properties identification. Specifically, in the early stage, geo-tile embeddings are firstly inferred through dynamic mobility events which are combinations of point-of-interest (POI) data and trajectory data by a Word2Vec-like model and metric learning. Then, in the latter stage, we use static street-level imagery to further enrich the embedding information by metric learning. Lastly, the framework learns distributed geo-tile embeddings for the given multi-modal data. We conduct experiments on real-world urban datasets. Four downstream tasks, i.e., main POI category classification task, main land use category classification task, restaurant average price regression task, and firm number regression task, are adopted for validating the effectiveness of the proposed framework in representing geo-tiles. Our proposed framework can significantly improve the performances of all downstream tasks. In addition, we also demonstrate that geo-tiles with similar urban region properties are geometrically closer in the vector space.
- [1] . 2018. Spatio-temporal matching for urban transportation applications. ACM Transactions on Spatial Algorithms and Systems 3, 4 (2018), 1–39.Google Scholar
Digital Library
- [2] . 2017. An approach for the discovery and validation of urban mobility patterns. Pervasive and Mobile Computing 42, 2 (
Dec. 2017), 77–92.Google ScholarDigital Library - [3] . 2018. Content-aware hierarchical point-of-interest embedding model for successive POI recommendation. In Proceedings of the 27th International Joint Conference on Artificial Intelligence. 3301–3307.Google ScholarDigital Library
- [4] . 2016. XGBoost: A scalable tree boosting system. In Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery, New York, NY, 785–794.Google ScholarDigital Library
- [5] . 2020. NexT: A framework for next-place prediction on location based social networks. Knowledge-Based Systems 204 (
Sept. 2020), 106205.Google ScholarCross Ref
- [6] . 2022. Investigating functional consistency of mobility-related urban zones via motion-driven embedding vectors and local POI-type distributions. Computational Urban Science 2, 1 (2022), 19.Google ScholarCross Ref
- [7] . 2019. Predicting neighborhoods’ socioeconomic attributes using restaurant data. Proceedings of the National Academy of Sciences 116, 31 (2019), 15447–15452.Google ScholarCross Ref
- [8] . 2021. A gridded establishment dataset as a proxy for economic activity in China. Scientific Data 8, 1 (2021), 1–9.Google ScholarCross Ref
- [9] . 2020. A deep learning approach for identifying user communities based on geographical preferences and its applications to urban and environmental planning. ACM Transactions on Spatial Algorithms and Systems 6, 3 (2020), 1–24.Google ScholarDigital Library
- [10] . 2019. Efficient region embedding with multi-view spatial networks: A perspective of locality-constrained spatial autocorrelations. Proceedings of the AAAI Conference on Artificial Intelligence 33, 01 (
July 2019), 906–913.Google ScholarDigital Library - [11] . 2017. Using deep learning and Google street view to estimate the demographic makeup of the US. Proceedings of the National Academy of Sciences 114 (
11 2017), 201700035.Google ScholarCross Ref - [12] . 2022. Place embedding across cities in location-based social networks. In Proceedings of the 37th ACM/SIGAPP Symposium on Applied Computing (2022-04-25). 539–546.Google ScholarDigital Library
- [13] . 2016. Deep residual learning for image recognition. In Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 770–778.Google ScholarCross Ref
- [14] . 2020. Accelerating land cover change in West Africa over four decades as population pressure increased. Communications Earth & Environment 1, 1 (2020), 1–10.Google ScholarCross Ref
- [15] . 2021. Urban function classification at road segment level using taxi trajectory data: A graph convolutional neural network approach. Computers, Environment and Urban Systems 87 (2021), 101619.Google ScholarCross Ref
- [16] . 2021. M3G: Learning urban neighborhood representation from multi-modal multi-graph. In Proceedings of the DeepSpatial 2021: 2nd ACM KDD Workshop on Deep Learning for Spatio-Temporal Data, Applications and Systems.Google Scholar
- [17] . 2022. Estimating urban functional distributions with semantics preserved POI embedding. International Journal of Geographical Information Science 0, 0 (2022), 1–26.Google Scholar
- [18] . 2019. Tile2Vec: Unsupervised representation learning for spatially distributed data. Proceedings of the AAAI Conference on Artificial Intelligence 33, 01 (
July 2019), 3967–3974.Google ScholarDigital Library - [19] . 2019. Unsupervised representation learning of spatial data via multimodal embedding. In Proceedings of the 28th ACM International Conference on Information and Knowledge Management. 1993–2002.Google ScholarDigital Library
- [20] . 2021. Transfer urban human mobility via POI embedding over multiple cities. ACM/IMS Transactions on Data Science 2, 1 (2021), 4:1–4:26.Google ScholarDigital Library
- [21] . 2019. An unsupervised approach to geographical knowledge discovery using street level and street network images. In Proceedings of the 3rd ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery. 56–65.Google ScholarDigital Library
- [22] . 2020. Estimation of regional economic development indicator from transportation network analytics. Scientific Reports 10, 1 (2020), 1–15.Google Scholar
- [23] . 2018. Analogical reasoning on chinese morphological and semantic relations. In Proceedings of the Annual Conference of the Association for Computational Linguistics. Association for Computational Linguistics, 138–143.Google ScholarCross Ref
- [24] . 2021. Pre-training context and time aware location embeddings from spatial-temporal trajectories for user next location prediction. Proceedings of the AAAI Conference on Artificial Intelligence 35, 5 (
May 2021), 4241–4248.Google ScholarCross Ref - [25] . 2016. Incorporating spatial interaction patterns in classifying and understanding urban land use. International Journal of Geographical Information Science 30, 2 (2016), 334–350.Google ScholarDigital Library
- [26] . 2012. Urban land uses and traffic “source-sink areas”: Evidence from GPS-enabled taxi data in Shanghai. Landscape and Urban Planning 106, 1 (2012), 73–87.Google ScholarCross Ref
- [27] . 2006. Use of impervious surface in urban land-use classification. Remote Sensing of Environment 102, 1–2 (2006), 146–160.Google ScholarCross Ref
- [28] Tomas Mikolov, Kai Chen, Gregory S. Corrado, and Jeffrey Dean. 2013. Efficient estimation of word representations in vector space. International Conference on Learning Representations, 1–12.Google Scholar
- [29] . 2013. Distributed representations of words and phrases and their compositionality. In Proceedings of the 26th International Conference on Neural Information Processing Systems - Volume 2. 3111–3119.Google ScholarDigital Library
- [30] . 2012. Land-use classification using taxi GPS traces. IEEE Transactions on Intelligent Transportation Systems 14, 1 (2012), 113–123.Google ScholarDigital Library
- [31] . 1901. LIII. On lines and planes of closest fit to systems of points in space. The London, Edinburgh, and Dublin Philosophical Magazine and Journal of Science 2, 11 (1901), 559–572.Google ScholarCross Ref
- [32] . 2014. A new insight into land use classification based on aggregated mobile phone data. International Journal of Geographical Information Science 28, 9 (2014), 1988–2007.Google ScholarDigital Library
- [33] . 2016. The Geography of Transport Systems.Google ScholarCross Ref
- [34] . 1988. Term-weighting approaches in automatic text retrieval. Information Processing & Management 24, 5 (1988), 513–523.Google ScholarDigital Library
- [35] . 2015. FaceNet: A unified embedding for face recognition and clustering. In Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 815–823.Google ScholarCross Ref
- [36] . 2020. Enabling finer grained place embeddings using spatial hierarchy from human mobility trajectories. In Proceedings of the 28th International Conference on Advances in Geographic Information Systems. 187–190.Google ScholarDigital Library
- [37] . 2021. Block2vec: An approach for identifying urban functional regions by integrating sentence embedding model and points of interest. ISPRS International Journal of Geo-Information 10, 5 (2021), 339.Google ScholarCross Ref
- [38] . 1970. A computer movie simulating urban growth in the detroit region. Economic Geography 46, Sup1 (1970), 234–240.Google ScholarCross Ref
- [39] . 2020. SeqST-GAN: Seq2Seq generative adversarial nets for multi-step urban crowd flow prediction. ACM Transactions on Spatial Algorithms and Systems 6, 4 (2020), Article 22.Google ScholarDigital Library
- [40] . 2020. Urban2Vec: Incorporating street view imagery and POIs for multi-modal urban neighborhood embedding. Proceedings of the AAAI Conference on Artificial Intelligence 34, 01 (
April 2020), 1013–1020.Google ScholarCross Ref - [41] . 2021. Representation learning of urban regions via mobility-signature-based zone embedding: A case study of Seoul, South Korea. In Proceedings of the 5th ACM SIGSPATIAL International Workshop on Location-Based Recommendations, Geosocial Networks and Geoadvertising (2021-11-02). 1–4.Google ScholarDigital Library
- [42] . 2019. City2City: Translating place representations across cities. In Proceedings of the 27th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (2019-11-05). 412–415.Google ScholarDigital Library
- [43] . 2017. From ITDL to Place2Vec: Reasoning about place type similarity and relatedness by learning embeddings from augmented spatial contexts. In Proceedings of the 25th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems. 1–10.Google ScholarDigital Library
- [44] . 2018. Representing urban functions through zone embedding with human mobility patterns. In Proceedings of the 27th International Joint Conference on Artificial Intelligence. 3919–3925.Google ScholarDigital Library
- [45] . 2020. Urban function recognition by integrating social media and street-level imagery. Environment and Planning B: Urban Analytics and City Science 48, 6 (2020), 1430–1444.Google Scholar
- [46] . 2012. Discovering regions of different functions in a city using human mobility and POIs. In Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery, New York, NY, 186–194.Google ScholarDigital Library
- [47] . 2015. Discovering urban functional zones using latent activity trajectories. IEEE Transactions on Knowledge and Data Engineering 27, 3 (2015), 712–725.Google ScholarDigital Library
- [48] . 2019. Beyond Word2vec: An approach for urban functional region extraction and identification by combining Place2vec and POIs. Computers, Environment and Urban Systems 74 (
March 2019), 1–12.Google ScholarCross Ref - [49] . 2021. A GloVe-Based POI type embedding model for extracting and identifying urban functional regions. ISPRS International Journal of Geo-Information 10, 6 (2021), 372.Google ScholarCross Ref
- [50] . 2017. Regions, periods, activities: Uncovering urban dynamics via cross-modal representation learning. In Proceedings of the 26th International Conference on World Wide Web (2017-04-03). 361–370.Google ScholarDigital Library
- [51] . 2020. Multi-view joint graph representation learning for urban region embedding. In Proceedings of the 29th International Joint Conference on Artificial Intelligence, Vol. 5. 4431–4437.Google ScholarCross Ref
- [52] . 2019. Unifying inter-region autocorrelation and intra-region structures for spatial embedding via collective adversarial learning. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 1700–1708.Google ScholarDigital Library
- [53] . 2014. Learning deep features for scene recognition using places database. In Proceedings of the Conference on Neural Information Processing Systems. MIT Press, Cambridge, MA, 487–495.Google Scholar
- [54] . 2017. Places: A 10 million image database for scene recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 40, 6 (2017), 1452–1464.Google Scholar
- [55] . 2018. DeepMove: Learning place representations through large scale movement data. In Proceedings of the 2018 IEEE International Conference on Big Data (Big Data). 2403–2412.Google ScholarCross Ref
Index Terms
- Geo-Tile2Vec: A Multi-Modal and Multi-Stage Embedding Framework for Urban Analytics
Recommendations
Urban Region Profiling via Multi-Graph Representation Learning
CIKM '22: Proceedings of the 31st ACM International Conference on Information & Knowledge ManagementProfiling urban regions is essential for urban analytics and planning. Although existing studies have made great efforts to learn urban region representation from multi-source urban data, there are still limitations on modelling local-level signals, ...
Urban Computing: Concepts, Methodologies, and Applications
Special Section on Urban ComputingUrbanization's rapid progress has modernized many people's lives but also engendered big issues, such as traffic congestion, energy consumption, and pollution. Urban computing aims to tackle these issues by using the data that has been generated in ...
Urban Informatics beyond Data: Media Architecture, Placemaking, and Citizen Action
UCUI '15: Proceedings of the ACM First International Workshop on Understanding the City with Urban InformaticsSince 2006, we have been conducting urban informatics research that we define as "the study, design, and practice of urban experiences across different urban contexts that are created by new opportunities of real-time, ubiquitous technology and the ...
Comments