Spatial-Net: A Self-Adaptive and Model-Agnostic Deep Learning Framework for Spatially Heterogeneous Datasets

Spatial-Net: A Self-Adaptive and Model-Agnostic Deep Learning Framework for Spatially Heterogeneous Datasets
复制标题

Spatial-Net:用于空间异构数据集的自适应且与模型无关的深度学习框架

DOI:
10.1145/3474717.3483970
复制
发表时间:
2021
期刊:
Proceedings of the 29th International Conference on Advances in Geographic Information Systems (SIGSPATIAL'21
影响因子:
--
通讯作者:
Ravirathinam, Praveen
Ravirathinam, Praveen
中科院分区:
--
文献类型:
--
作者:
Xie, Yiqun;Jia, Xiaowei;Bao, Han;Zhou, Xun;Yu, Jia;Ghosh, Rahul;Ravirathinam, Praveen

文献摘要

参考文献

被引文献

相似文献

从空间数据中发现知识对于许多重要的社会应用至关重要,包括作物监测、太阳能估计、交通预测和公共卫生。本文旨在解决深度学习背景下空间数据带来的关键挑战——通常嵌入其生成过程中的内在空间异质性。在相关工作中,卷积神经网络的早期兴起显示了深层架构中显式空间感知的有希望的价值(即输入单元之间的空间结构的保存和局部连接的使用)。然而,空间异质性问题尚未得到充分探讨。虽然最近的发展试图纳入对空间变异性的认识(例如 SVANN),但这些方法要么依赖于手动定义的空间分区,要么由于训练数据的减少而仅支持非常有限的分区(例如,两个)。为了解决这些限制,我们提出了一个空间网络,通过基于重要性的增长和折叠(SIG-GAC)框架来同时学习空间分区方案和深度网络架构。 SIG-GAC 允许分区之间进行协作训练,并使用指数缩减树来控制网络大小。使用真实数据集的实验表明,Spatial-Net 可以自动学习异构空间过程背后的模式,并极大地提高模型性能。
Knowledge discovery from spatial data is essential for many important societal applications including crop monitoring, solar energy estimation, traffic prediction and public health. This paper aims to tackle a key challenge posed by spatial data - the intrinsic spatial heterogeneity commonly embedded in their generation processes - in the context of deep learning. In related work, the early rise of convolutional neural networks showed the promising value of explicit spatial-awareness in deep architectures (i.e., preservation of spatial structure among input cells and the use of local connection). However, the issue of spatial heterogeneity has not been sufficiently explored. While recent developments have tried to incorporate awareness of spatial variability (e.g., SVANN), these methods either rely on manually-defined space partitioning or only support very limited partitions (e.g., two) due to reduction of training data. To address these limitations, we propose a Spatial-Net to simultaneously learn a space-partitioning scheme and a deep network architecture with a Significance-based Grow-and-Collapse (SIG-GAC) framework. SIG-GAC allows collaborative training between partitions and uses an exponential reduction tree to control the network size. Experiments using real-world datasets show that Spatial-Net can automatically learn the pattern underlying heterogeneous spatial process and greatly improve model performance.
迈向空间变异感知深度神经网络 (SVANN):结果摘要
DOI: --
发表时间: 2020
期刊: arXiv.org
影响因子: --
作者:
Jayant Gupta;Yiqun Xie;S. Shekhar
通讯作者: S. Shekhar
基于深度学习的地理空间对象检测的无监督增强框架:结果摘要
DOI: 10.1145/3274895.3274901
发表时间: 2018
期刊: Proceedings of the 26th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems
影响因子: --
作者:
Xie, Yiqun;Bhojwani, Rahul;Shekhar, Shashi;Knight, Joseph
通讯作者: Knight, Joseph
DOI: 10.1038/nbt1209-1135
发表时间: 2009-12
影响因子: 46.9
作者:
Noble, William S.
通讯作者: Noble, William S.
DOI: 10.1145/3337798
发表时间: 2019-08-01
影响因子: 5
作者:
Jiang, Zhe;Sainju, Arpan Man;Knight, Joseph
通讯作者: Knight, Joseph