Multi-Scale Representation Learning for Spatial Feature Distributions using Grid Cells

by   Gengchen Mai, et al.

Unsupervised text encoding models have recently fueled substantial progress in NLP. The key idea is to use neural networks to convert words in texts to vector space representations based on word positions in a sentence and their contexts, which are suitable for end-to-end training of downstream tasks. We see a strikingly similar situation in spatial analysis, which focuses on incorporating both absolute positions and spatial contexts of geographic objects such as POIs into models. A general-purpose representation model for space is valuable for a multitude of tasks. However, no such general model exists to date beyond simply applying discretization or feed-forward nets to coordinates, and little effort has been put into jointly modeling distributions with vastly different characteristics, which commonly emerges from GIS data. Meanwhile, Nobel Prize-winning Neuroscience research shows that grid cells in mammals provide a multi-scale periodic representation that functions as a metric for location encoding and is critical for recognizing places and for path-integration. Therefore, we propose a representation learning model called Space2Vec to encode the absolute positions and spatial relationships of places. We conduct experiments on two real-world geographic data for two different tasks: 1) predicting types of POIs given their positions and context, 2) image classification leveraging their geo-locations. Results show that because of its multi-scale representations, Space2Vec outperforms well-established ML approaches such as RBF kernels, multi-layer feed-forward nets, and tile embedding approaches for location modeling and image classification tasks. Detailed analysis shows that all baselines can at most well handle distribution at one scale but show poor performances in other scales. In contrast, Space2Vec's multi-scale representation can handle distributions at different scales.


Sphere2Vec: Multi-Scale Representation Learning over a Spherical Surface for Geospatial Predictions

Generating learning-friendly representations for points in a 2D space is...

Sphere2Vec: A General-Purpose Location Representation Learning over a Spherical Surface for Large-Scale Geospatial Predictions

Generating learning-friendly representations for points in space is a fu...

Learning scale-variant and scale-invariant features for deep image classification

Convolutional Neural Networks (CNNs) require large image corpora to be t...

Towards General-Purpose Representation Learning of Polygonal Geometries

Neural network representation learning for spatial data is a common need...

MC-DGCNN: A Novel DNN Architecture for Multi-Category Point Set Classification

Point set classification aims to build a representation learning model t...

CropMix: Sampling a Rich Input Distribution via Multi-Scale Cropping

We present a simple method, CropMix, for the purpose of producing a rich...

Masked Image Modeling with Local Multi-Scale Reconstruction

Masked Image Modeling (MIM) achieves outstanding success in self-supervi...

Please sign up or login with your details

Forgot password? Click here to reset