Cross-City Latent Space Alignment for Consistency Region Embedding
(2025) 42nd International Conference on Machine Learning, ICML 2025 267. p.8261-8274- Abstract
Learning urban region embeddings has substantially advanced urban analysis, but their typical focus on individual cities leads to disparate embedding spaces, hindering cross-city knowledge transfer and the reuse of downstream task predictors. To tackle this issue, we present Consistency Region Embedding (CoRE), a unified framework integrating region embedding learning with crosscity latent space alignment. CoRE first embeds regions from two cities into separate latent spaces, followed by the alignment of latent space manifolds and fine-grained individual regions from both cities. This ensures compatible and comparable embeddings within aligned latent spaces, enabling predictions of various socioeconomic indicators without ground truth... (More)
Learning urban region embeddings has substantially advanced urban analysis, but their typical focus on individual cities leads to disparate embedding spaces, hindering cross-city knowledge transfer and the reuse of downstream task predictors. To tackle this issue, we present Consistency Region Embedding (CoRE), a unified framework integrating region embedding learning with crosscity latent space alignment. CoRE first embeds regions from two cities into separate latent spaces, followed by the alignment of latent space manifolds and fine-grained individual regions from both cities. This ensures compatible and comparable embeddings within aligned latent spaces, enabling predictions of various socioeconomic indicators without ground truth labels by migrating knowledge from label-rich cities. Extensive experiments show CoRE outperforms competitive baselines, confirming its effectiveness for crosscity knowledge transfer via aligned latent spaces.
(Less)
- author
- Chen, Meng ; Jia, Hongwei ; Li, Zechen ; Jia, Wenzhen ; Zhao, Kai ; Dai, Hongjun and Huang, Weiming LU
- organization
- publishing date
- 2025
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- Proceedings of Machine Learning Research
- volume
- 267
- pages
- 14 pages
- publisher
- ML Research Press
- conference name
- 42nd International Conference on Machine Learning, ICML 2025
- conference location
- Vancouver, Canada
- conference dates
- 2025-07-13 - 2025-07-19
- external identifiers
-
- scopus:105023569398
- language
- English
- LU publication?
- yes
- additional info
- Publisher Copyright: © 2025 by the author(s).
- id
- 7fe43dc7-df21-43db-96c0-4a76e2b47535
- date added to LUP
- 2026-02-03 16:08:55
- date last changed
- 2026-02-03 16:09:24
@inproceedings{7fe43dc7-df21-43db-96c0-4a76e2b47535,
abstract = {{<p>Learning urban region embeddings has substantially advanced urban analysis, but their typical focus on individual cities leads to disparate embedding spaces, hindering cross-city knowledge transfer and the reuse of downstream task predictors. To tackle this issue, we present Consistency Region Embedding (CoRE), a unified framework integrating region embedding learning with crosscity latent space alignment. CoRE first embeds regions from two cities into separate latent spaces, followed by the alignment of latent space manifolds and fine-grained individual regions from both cities. This ensures compatible and comparable embeddings within aligned latent spaces, enabling predictions of various socioeconomic indicators without ground truth labels by migrating knowledge from label-rich cities. Extensive experiments show CoRE outperforms competitive baselines, confirming its effectiveness for crosscity knowledge transfer via aligned latent spaces.</p>}},
author = {{Chen, Meng and Jia, Hongwei and Li, Zechen and Jia, Wenzhen and Zhao, Kai and Dai, Hongjun and Huang, Weiming}},
booktitle = {{Proceedings of Machine Learning Research}},
language = {{eng}},
pages = {{8261--8274}},
publisher = {{ML Research Press}},
title = {{Cross-City Latent Space Alignment for Consistency Region Embedding}},
volume = {{267}},
year = {{2025}},
}