Research map / Learning theory and algorithms / Clustering
DBSCAN++: Towards fast and scalable density clustering
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 |
|---|---|---|---|
| Compute densities for a selected subset of points instead of every point | DBSCAN++ vs DBSCAN · 11 real datasets | adjusted RAND index | Mixed |
| Compute densities for a selected subset of points instead of every point | DBSCAN++ vs DBSCAN · 11 real datasets | runtime | Helped |
| Use greedy K-center rather than uniform sampling to select query points (ablation) | DBSCAN++ · 11 real datasets | clustering scores | Helped |
| Use greedy K-center rather than uniform sampling to select query points (ablation) | DBSCAN++ · 11 real datasets | runtime | Helped |
| Use greedy K-center initialization and m/n=0.1 (ablation) | DBSCAN++ · Synthetic 10,000-point, 50-dimensional dataset | clustering performance | Helped |
| Use greedy K-center initialization and m/n=0.1 (ablation) | DBSCAN++ · Synthetic 10,000-point, 50-dimensional dataset | runtime | Helped |
| Use DBSCAN++ with K-center initialization instead of DBSCAN | DBSCAN++ · 988×750 image segmentation | runtime: 44.18 seconds -> 7.38 seconds | Helped |
| Reduce the sampled subset size m (ablation) | DBSCAN++ · Clustering datasets | clustering scores | Hurt |
| Use a subset of core-points rather than all core-points | DBSCAN++ vs DBSCAN · Clustering datasets across epsilon settings | robustness to epsilon | Helped |
Closest papers by meaning
- Faster DBSCAN via subsampled similarity queries (NeurIPS 2020 · similarity 0.92)
- Scalable DBSCAN with Random Projections (NeurIPS 2024 · similarity 0.91)
- Almost Linear Time Density Level Set Estimation via DBSCAN (AAAI 2021 · similarity 0.91)
- Nearest-Neighbour-Induced Isolation Similarity and Its Impact on Density-Based Clustering (AAAI 2019 · similarity 0.89)
- Incremental Density-Based Clustering with Grid Partitioning (Student Abstract) (AAAI 2023 · similarity 0.88)
- Enhanced Denesity Peak Clustering for High-Dimensional Data (AAAI 2025 · 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.