Jointly Learning Representations for Map Entities via Heterogeneous Graph Contrastive Learning

TL;DR

This paper introduces HOME-GCL, a novel self-supervised heterogeneous graph contrastive learning method that jointly learns representations for multiple map entity types, improving integration and performance in geographic information systems.

Contribution

It proposes a unified framework for learning map entity representations across categories using a heterogeneous graph transformer and contrastive learning, addressing limitations of prior single-category methods.

Findings

Outperforms existing methods on large-scale datasets.

Effectively integrates diverse map entities into a unified representation.

Demonstrates superiority in multiple downstream tasks.

Abstract

The electronic map plays a crucial role in geographic information systems, serving various urban managerial scenarios and daily life services. Developing effective Map Entity Representation Learning (MERL) methods is crucial to extracting embedding information from electronic maps and converting map entities into representation vectors for downstream applications. However, existing MERL methods typically focus on one specific category of map entities, such as POIs, road segments, or land parcels, which is insufficient for real-world diverse map-based applications and might lose latent structural and semantic information interacting between entities of different types. Moreover, using representations generated by separate models for different map entities can introduce inconsistencies. Motivated by this, we propose a novel method named HOME-GCL for learning representations of multiple categories of map entities. Our approach utilizes a heterogeneous map entity graph (HOME graph) that integrates both road segments and land parcels into a unified framework. A HOME encoder with parcel-segment joint feature encoding and heterogeneous graph transformer is then deliberately designed to convert segments and parcels into representation vectors. Moreover, we introduce two types of contrastive learning tasks, namely intra-entity and inter-entity tasks, to train the encoder in a self-supervised manner. Extensive experiments on three large-scale datasets covering road segment-based, land parcel-based, and trajectory-based tasks demonstrate the superiority of our approach. To the best of our knowledge, HOME-GCL is the first attempt to jointly learn representations for road segments and land parcels using a unified model.