Academic Journal
Predicting human mobility via Graph Convolutional Dual-attentive Networks
| العنوان: | Predicting human mobility via Graph Convolutional Dual-attentive Networks |
|---|---|
| المؤلفون: | Dang, Weizhen, Wang, Haibo, Pan, Shirui, Zhang, Pei, Zhou, Chuan, Chen, Xin, Wang, Jilong |
| المساهمون: | Nagarkar, Parth |
| المصدر: | Dang , W , Wang , H , Pan , S , Zhang , P , Zhou , C , Chen , X & Wang , J 2022 , Predicting human mobility via Graph Convolutional Dual-attentive Networks . in P Nagarkar (ed.) , Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining . Association for Computing Machinery (ACM) , New York NY USA , pp. 192-200 , ACM International Conference on Web Search and Data Mining 2022 , Online , United States of America , 21/02/22 . https://doi.org/10.1145/3488560.3498400 |
| بيانات النشر: | Association for Computing Machinery (ACM) |
| سنة النشر: | 2022 |
| مصطلحات موضوعية: | Attention mechanism, Graph convolution, Mobility prediction, Sequential modeling |
| الوصف: | Human mobility prediction is of great importance for various applications such as smart transportation and personalized recommender systems. Although many traditional pattern-based methods and deep models ($e.g.,$ recurrent neural networks) based methods have been developed for this task, they essentially do not well cope with the sparsity and inaccuracy of trajectory data and the complicated high-order nature of the sequential dependency, which are typical challenges in mobility prediction. To solve the problems, this paper proposes a novel framework named G raph C onvolutional D ual-a ttentive N etworks (GCDAN), which consists of two modules: spatio-temporal embedding and trajectory encoder-decoder. The first module employs a bidirectional diffusion graph convolution to preserve the spatial dependency in the location embedding. The second module employs a dual-attentive mechanism based on a Sequence to Sequence architecture to effectively extract the long-range sequential dependency within a trajectory and the correlation between different trajectories for predictions. Extensive experiments on three real-world datasets show that GCDAN achieves significant performance gain compared with state-of-the-art baselines. |
| نوع الوثيقة: | article in journal/newspaper |
| وصف الملف: | application/pdf |
| اللغة: | English |
| ردمك: | 978-1-4503-9132-0 1-4503-9132-X |
| Relation: | urn:ISBN:9781450391320 |
| DOI: | 10.1145/3488560.3498400 |
| الاتاحة: | https://research.monash.edu/en/publications/05db6a89-f6dc-46f6-a445-f6bf887f2719 https://doi.org/10.1145/3488560.3498400 https://researchmgt.monash.edu/ws/files/404751600/374415544_oa.pdf http://www.scopus.com/inward/record.url?scp=85125813580&partnerID=8YFLogxK |
| Rights: | info:eu-repo/semantics/openAccess |
| رقم الانضمام: | edsbas.40DCD0BC |
| قاعدة البيانات: | BASE |
| ردمك: | 9781450391320 145039132X |
|---|---|
| DOI: | 10.1145/3488560.3498400 |