This research paper explores the application of graph-based deep learning to map generalization, specifically for simplifying and aggregating building footprints. The study evaluates graph neural network architectures like GCN, GAT, and GraphSAGE, finding that GraphSAGE performs well in link prediction for aggregation but faces challenges in precise node movement prediction for simplification. The findings indicate that map aggregation is more complex than simplification for current deep learning models, highlighting areas for future methodological development. AI
IMPACT This research could lead to more sophisticated automated map generalization tools by leveraging advanced deep learning techniques.
RANK_REASON The cluster contains a research paper published on arXiv detailing novel applications of graph-based deep learning.
- graph attention network
- graph convolutional network
- Graphsage
- alphaXiv
- arXiv
- CatalyzeX Code Finder for Papers
- CORE Recommender
- DagsHub
- Gotit.pub
- Hugging Face
- IArxiv Recommender
- Influence Flower
- ScienceCast
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
