Urban Region Representation Learning with Attentive Fusion

arXiv:2312.04606v2 Announce Type: replace
Abstract: An increasing number of related urban data sources have brought forth novel opportunities for learning urban region representations, i.e., embeddings. The embeddings describe latent features of urban regions and enable discovering similar regions for urban planning applications. Existing methods learn an embedding for a region using every different type of region feature data, and subsequently fuse all learned embeddings of a region to generate a unified region embedding. However, these studies often overlook the significance …

abstract applications arxiv cs.db cs.lg data data sources embedding embeddings every features fusion learn novel opportunities planning representation representation learning type urban urban planning