期刊
2022 IEEE INTERNATIONAL CONFERENCE ON DATA MINING (ICDM)
卷 -, 期 -, 页码 1293-1298出版社
IEEE
DOI: 10.1109/ICDM54844.2022.00170
关键词
unseen domain generalization; spatial; GNN; edge embedding; interpolation
资金
- National Science Foundation(NSF) [1755850, 1841520, 2007716, 2007976, 1942594, 1907805]
- Jeffress Memorial Trust Award
- Amazon Research Award
- NVIDIA GPU Grant
- Design Knowledge Company [10827.002.120.04]
This paper proposes a generic framework for spatial domain generalization based on spatial data, and develops a spatial interpolation graph neural network to handle spatial data and learn spatial embeddings. It addresses the issue of poor performance of traditional machine learning models in the presence of spatial autocorrelation and spatial heterogeneity.
Spatial autocorrelation and spatial heterogeneity widely exist in spatial data, which make the traditional machine learning model perform badly. Spatial domain generalization is a spatial extension of domain generalization, which can generalize to unseen spatial domains in continuous 2D space. Specifically, it learns a model under varying data distributions that generalizes to unseen domains. Although tremendous success has been achieved in domain generalization, there exist very few works on spatial domain generalization. The advancement of this area is challenged by: 1) Difficulty in characterizing spatial heterogeneity, and 2) Difficulty in obtaining predictive models for unseen locations without training data. To address these challenges, this paper proposes a generic framework for spatial domain generalization. Specifically, We develop the spatial interpolation graph neural network 1 that handles spatial data as a graph and learns the spatial embedding on each node and their relationships. The spatial interpolation graph neural network infers the spatial embedding of an unseen location during the test phase. Then the spatial embedding of the target location is used to decode the parameters of the downstream-task model directly on the target location. Finally, extensive experiments on ten realworld datasets demonstrate the proposed method's strength.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据