Multi-View Joint Graph Representation Learning for Urban Region Embedding

Authors: Mingyang Zhang, Tong Li, Yong Li, Pan Hui

IJCAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiment results demonstrate that by exploiting our proposed joint learning model, the performance is improved by a large margin on both tasks compared with the state-of-the-art methods.
Researcher Affiliation Academia Mingyang Zhang1 , Tong Li1,3 , Yong Li2 and Pan Hui1,3 1The Hong Kong University of Science and Technology 2Tsinghua University 3University of Helsinki
Pseudocode No The paper does not contain any pseudocode or clearly labeled algorithm blocks.
Open Source Code Yes Please refer to the released code2 for details of the implementations. 2https://github.com/mingyangzhang/mv-region-embedding
Open Datasets Yes We collect several real-world datasets of New York City from NYC open data website1. The description of each dataset is shown in Table 1. 1opendata.cityofnewyork.us
Dataset Splits Yes compute all the metrics by K-Fold cross-validation, where K=5.
Hardware Specification No The paper does not provide any specific hardware details such as GPU or CPU models used for running experiments.
Software Dependencies No The paper refers to various models and algorithms (e.g., GAT, GAE, node2vec, K-means, Lasso regression) but does not specify any software dependencies with version numbers (e.g., Python, PyTorch, TensorFlow versions or library versions).
Experiment Setup Yes The embedding sizes of CHK and Po I are the number of check-in and Po I categories, respectively. The embedding size of HDGE and ZE-Mob are set as 20 and 96 as suggested by the authors. The embedding sizes of GAE, node2vec, MV-PN, our model and variants are set as 96.