Improving the Computational Efficiency and Explainability of GeoAggregator

TL;DR

This paper enhances the GeoAggregator deep learning model for geospatial data by improving its computational efficiency and explainability through optimized data processing, ensembling, and a post-hoc explanation framework, validated on synthetic datasets.

Contribution

It introduces an optimized pipeline and explainability methods for GeoAggregator, improving its speed and interpretability over prior versions.

Findings

Improved prediction accuracy and inference speed of GeoAggregator.

Effective capture of spatial effects in synthetic datasets.

Enhanced model explainability using GeoShapley framework.

Abstract

Accurate modeling and explaining geospatial tabular data (GTD) are critical for understanding geospatial phenomena and their underlying processes. Recent work has proposed a novel transformer-based deep learning model named GeoAggregator (GA) for this purpose, and has demonstrated that it outperforms other statistical and machine learning approaches. In this short paper, we further improve GA by 1) developing an optimized pipeline that accelerates the dataloading process and streamlines the forward pass of GA to achieve better computational efficiency; and 2) incorporating a model ensembling strategy and a post-hoc model explanation function based on the GeoShapley framework to enhance model explainability. We validate the functionality and efficiency of the proposed strategies by applying the improved GA model to synthetic datasets. Experimental results show that our implementation improves the prediction accuracy and inference speed of GA compared to the original implementation. Moreover, explanation experiments indicate that GA can effectively captures the inherent spatial effects in the designed synthetic dataset. The complete pipeline has been made publicly available for community use (https://github.com/ruid7181/GA-sklearn).