arXiv cs.AI· Lakshay Sharma, Alex Marin·· 12 小时前AI 评分22
通过反向地理编码学习行政边界感知的位置编码器
Learning Administrative Boundary-Aware Location Encoders via Reverse Geocoding
AI 导读
研究者提出首个利用反向地理编码文本作为自监督信号、学习行政边界感知位置编码器的方法，可套用于现有位置编码器架构并稳定提升下游任务表现。团队还推出专为反向地理编码监督设计的 RevGeoRQ 架构，在多项下游任务上超过现有位置编码器。该方法借助人类可读的反向地理编码字符串与残差量化语义 ID，提供比现有方案更可解释的地理位置表示，代码与模型权重即将发布。
正文 · 原文
Abstract:Location encoders learn compact representations of latitude--longitude coordinates for downstream geospatial prediction tasks. Existing approaches are pretrained using continuous or naturally occurring supervision, such as imagery, climate variables, or species distributions, and therefore do not explicitly capture administrative boundaries or place names, despite their strong influence on many real-world geospatial phenomena. We introduce, to our knowledge, the first method for learning administrative boundary-aware location encoders, using reverse-geocoded text as a self-supervised training signal. Our approach can be applied to existing location encoder architectures and consistently improves their downstream performance. We further introduce RevGeoRQ, a custom architecture tailored to reverse-geocoding supervision, which yields additional gains and exceeds contemporary location encoders on several downstream tasks. Finally, the use of human-interpretable reverse-geocoded strings and residual-quantized semantic IDs provides a more interpretable representation of geographic location than existing approaches. Code and model weights to be released soon.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.24306 [cs.LG] |
| (or arXiv:2610.24306v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.24306 arXiv-issued DOI via DataCite |
Submission history
From: Lakshay Sharma [view email]
[v1]
Fri, 16 Oct 2026 23:10:58 UTC (3,664 KB)
[v2]
Tue, 20 Oct 2026 16:56:57 UTC (3,664 KB)
来源：arXiv cs.AI · arxiv.org