Abstract
Geospatial region embeddings are vital in developing predictive models tailored to urban environments. Such models enable critical applications, including crime rate prediction and land usage classification. However, state-of-the-art methods typically generate embeddings based on fixed administrative regions. These regions may not always align with specific tasks or areas of user interest. Creating fine-grained embeddings tailored to specific tasks and regions of user interest is labor-intensive and requires substantial resources. In this paper, we propose MAGRE – a novel approach that generates fine-granular adaptive geospatial region embeddings by leveraging multimodal and multitask learning. The embeddings generated by MAGRE can be flexibly aggregated to suit various region boundaries, rendering them effective in diverse urban applications. Our experimental results demonstrate that MAGRE’s embeddings outperform state-of-the-art embedding baselines, resulting in a 25.73% reduction in root mean squared error for crime rate prediction and a 19.08% reduction for check-in count prediction.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
OpenStreetMap: https://www.openstreetmap.org/. The OpenStreetMap name is a trademark of the OpenStreetMap Foundation and is used with their permission. We are not endorsed by or affiliated with the OpenStreetMap Foundation.
- 2.
References
Bartunov, S., Kondrashkin, D., Osokin, A., Vetrov, D.P.: Breaking sticks and ambiguities with adaptive skip-gram. In: AISTATS 2016. JMLR.org (2016)
Berg, B.F.: New York City Politics: Governing Gotham. Rutgers University Press, New Brunswick (2007)
Birch, C.P., Oom, S.P., Beecham, J.A.: Rectangular and hexagonal grids used for observation, experiment and simulation in ecology. Ecol. Model. 206(3–4), 347–359 (2007)
Fu, Y., Wang, P., Du, J., Wu, L., Li, X.: Efficient region embedding with multi-view spatial networks: a perspective of locality-constrained spatial autocorrelations. In: AAAI 2019, pp. 906–913. AAAI Press (2019)
Girshick, R.B.: Fast R-CNN. In: IEEE, ICCV 2015, pp. 1440–1448. IEEE Computer Society (2015)
Li, Y., Huang, W., Cong, G., Wang, H., Wang, Z.: Urban region representation learning with openstreetmap building footprints. In: ACM SIGKDD. ACM (2023)
Reimers, N., Gurevych, I.: Sentence-bert: sentence embeddings using siamese bert-networks. In: EMNLP-IJCNLP 2019. ACL (2019)
Tan, M., Le, Q.V.: Efficientnet: rethinking model scaling for convolutional neural networks. In: ICML 2019, pp. 6105–6114. PMLR (2019)
Velickovic, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., Bengio, Y.: Graph attention networks. In: ICLR 2018. OpenReview.net (2018)
Wang, H., Li, Z.: Region representation learning via mobility flow. In: ACM, CIKM 2017, pp. 237–246. ACM (2017)
Wozniak, S., Szymanski, P.: hex2vec: context-aware embedding H3 hexagons with openstreetmap tags. In: GeoAI@SIGSPATIAL 2021, pp. 61–71. ACM (2021)
Wu, S., et al.: Multi-graph fusion networks for urban region embedding. In: IJCAI 2022 (2022)
Xi, Y., Li, T., Wang, H., Li, Y., Tarkoma, S., Hui, P.: Beyond the first law of geography: learning representations of satellite imagery by leveraging point-of-interests. In: WWW 2022, pp. 3308–3316. ACM (2022)
Yao, Z., Fu, Y., Liu, B., Hu, W., Xiong, H.: Representing urban functions through zone embedding with human mobility patterns. In: IJCAI 2018 (2018)
Zhang, M., Li, T., Li, Y., Hui, P.: Multi-view joint graph representation learning for urban region embedding. In: IJCAI 2020, pp. 4431–4437. ijcai.org (2020)
Zhou, S., He, D., Chen, L., Shang, S., Han, P.: Heterogeneous region embedding with prompt learning. In: AAAI 2023. AAAI Press (2023)
Acknowledgements:
This work was partially funded by the Federal Ministry for Economic Affairs and Climate Action (BMWK), Germany (“ATTENTION!”, 01MJ22012C).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Dadwal, R., Yu, R., Demidova, E. (2024). A Multimodal and Multitask Approach for Adaptive Geospatial Region Embeddings. In: Yang, DN., Xie, X., Tseng, V.S., Pei, J., Huang, JW., Lin, J.CW. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2024. Lecture Notes in Computer Science(), vol 14649. Springer, Singapore. https://doi.org/10.1007/978-981-97-2262-4_29
Download citation
DOI: https://doi.org/10.1007/978-981-97-2262-4_29
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-2264-8
Online ISBN: 978-981-97-2262-4
eBook Packages: Computer ScienceComputer Science (R0)