Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 10, 2025ACM Transactions on Knowledge Discovery from Data

SE-GCL: A Semantic-Enhanced Graph Contrastive Learning Framework for Road Network Embedding

View Full Paper
Ask AI
Bookmark
Share

Authors

JZJie ZhaoCCChao ChenWZWanyi Zhang

Discussion

Loading...

Member takes

Overview

Novel framework enhances road network embeddings using multi-modal data and contrastive learning techniques.

Key Points

  • SE-GCL outperforms existing methods in generating robust road network representations, enhancing task performance.
  • The framework effectively utilizes mobility semantics and geo-locality to improve representation learning quality.
  • Experimentation on real-world road networks shows significant performance gains across multiple traffic-related tasks.
  • Incorporating multi-modal features helps capture essential attribute and visual information of road segments.

Cite This Study

Zhao et al. (2025) studied this question.

synapsesocial.com/papers/68c1afcd54b1d3bfb60e7f0ahttps://doi.org/10.1145/3757921
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Semantic-enhanced Heterogeneous Graph Contrastive Learning for Recommendation2024 · 1 citations
  2. 2Jointly Learning Representations for Map Entities via Heterogeneous Graph Contrastive Learning2024 · 2 citations
  3. 3Smoothed Graph Contrastive Learning via Seamless Proximity Integration2024
  4. 4Structure-enhanced Contrastive Learning for Graph Clustering2024
  5. 5L^2CL: Embarrassingly Simple Layer-to-Layer Contrastive Learning for Graph Collaborative Filtering2024 · 1 citations