De-coupled NeuroGF for Shortest Path Distance Approximations on Large Terrain Graphs

Samantha Chen, Pankaj K Agarwal, Yusu Wang
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:7648-7663, 2025.

Abstract

The ability to acquire high-resolution, large-scale geospatial data at an unprecedented using LiDAR and other related technologies has intensified the need for scalable algorithms for terrain analysis, including shortest-path-distance (SPD) queries on large-scale terrain digital elevation models (DEMs). In this paper, we present a neural data structure for efficiently answering SPD queries approximately on a large terrain DEM, which is based on the recently proposed neural geodesic field (NeuroGF) framework (Zhang et al., 2023)—the state-of-the-art neural data structure for estimating geodesic distance. In particular, we propose a decoupled-NeuroGF data structure combined with an efficient two-stage mixed-training strategy, which significantly reduces computational bottlenecks and enables efficient training on terrain DEMs at a scale not feasible before. We demonstrate the efficacy of our approach by performing detailed experiments on both synthetic and real data sets. For instance, we can train a small model with around 70000 parameters on a terrain DEM with 16 million nodes in a matter of hours that can answer SPD queries with 1% relative error in at most 10ms per query.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-chen25a, title = {De-coupled {N}euro{GF} for Shortest Path Distance Approximations on Large Terrain Graphs}, author = {Chen, Samantha and Agarwal, Pankaj K and Wang, Yusu}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {7648--7663}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/chen25a/chen25a.pdf}, url = {https://proceedings.mlr.press/v267/chen25a.html}, abstract = {The ability to acquire high-resolution, large-scale geospatial data at an unprecedented using LiDAR and other related technologies has intensified the need for scalable algorithms for terrain analysis, including shortest-path-distance (SPD) queries on large-scale terrain digital elevation models (DEMs). In this paper, we present a neural data structure for efficiently answering SPD queries approximately on a large terrain DEM, which is based on the recently proposed neural geodesic field (NeuroGF) framework (Zhang et al., 2023)—the state-of-the-art neural data structure for estimating geodesic distance. In particular, we propose a decoupled-NeuroGF data structure combined with an efficient two-stage mixed-training strategy, which significantly reduces computational bottlenecks and enables efficient training on terrain DEMs at a scale not feasible before. We demonstrate the efficacy of our approach by performing detailed experiments on both synthetic and real data sets. For instance, we can train a small model with around 70000 parameters on a terrain DEM with 16 million nodes in a matter of hours that can answer SPD queries with 1% relative error in at most 10ms per query.} }
Endnote
%0 Conference Paper %T De-coupled NeuroGF for Shortest Path Distance Approximations on Large Terrain Graphs %A Samantha Chen %A Pankaj K Agarwal %A Yusu Wang %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-chen25a %I PMLR %P 7648--7663 %U https://proceedings.mlr.press/v267/chen25a.html %V 267 %X The ability to acquire high-resolution, large-scale geospatial data at an unprecedented using LiDAR and other related technologies has intensified the need for scalable algorithms for terrain analysis, including shortest-path-distance (SPD) queries on large-scale terrain digital elevation models (DEMs). In this paper, we present a neural data structure for efficiently answering SPD queries approximately on a large terrain DEM, which is based on the recently proposed neural geodesic field (NeuroGF) framework (Zhang et al., 2023)—the state-of-the-art neural data structure for estimating geodesic distance. In particular, we propose a decoupled-NeuroGF data structure combined with an efficient two-stage mixed-training strategy, which significantly reduces computational bottlenecks and enables efficient training on terrain DEMs at a scale not feasible before. We demonstrate the efficacy of our approach by performing detailed experiments on both synthetic and real data sets. For instance, we can train a small model with around 70000 parameters on a terrain DEM with 16 million nodes in a matter of hours that can answer SPD queries with 1% relative error in at most 10ms per query.
APA
Chen, S., Agarwal, P.K. & Wang, Y.. (2025). De-coupled NeuroGF for Shortest Path Distance Approximations on Large Terrain Graphs. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:7648-7663 Available from https://proceedings.mlr.press/v267/chen25a.html.

Related Material