Research map / Graph learning / Graph algorithms and clustering
Faster DBSCAN via subsampled similarity queries
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Subsample the epsilon-neighborhood graph instead of constructing the full graph | DBSCAN · Australian | runtime: over 200x speedup | Helped |
| Subsample the epsilon-neighborhood graph instead of constructing the full graph | DBSCAN · Still | RAM usage: over 250x reduction in RAM | Helped |
| Subsample neighborhood edges while retaining all data points | DBSCAN · Large datasets | ARI | No clear effect |
| Subsample neighborhood edges while retaining all data points | DBSCAN · Large datasets | runtime | Mixed |
| Use SNG-DBSCAN rather than DBSCAN++ with the same sampling rate | DBSCAN++ · Large datasets | clustering metrics: 70% of the metrics | Mixed |
| Use a smaller edge sampling rate (ablation) | SNG-DBSCAN · Simulated uniform balls | ARI | Helped |
| Vary the edge sampling rate (ablation) | SNG-DBSCAN · Smaller datasets | clustering quality | No clear effect |
Closest papers by meaning
- DBSCAN++: Towards fast and scalable density clustering (ICML 2019 · similarity 0.92)
- Nearest-Neighbour-Induced Isolation Similarity and Its Impact on Density-Based Clustering (AAAI 2019 · similarity 0.89)
- Scalable DBSCAN with Random Projections (NeurIPS 2024 · similarity 0.89)
- Fast Local Search Algorithms for Clustering with Adaptive Sampling and Bandit Strategies (NeurIPS 2025 · similarity 0.87)
- New Parallel and Streaming Algorithms for Directed Densest Subgraph (NeurIPS 2025 · similarity 0.87)
- Faster Streaming and Scalable Algorithms for Finding Directed Dense Subgraphs in Large Graphs (ICML 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.