Research map / Learning theory and algorithms / Clustering
Coresets for Relational Data and The Applications
Jiaxiang Chen, Qingyuan Yang, Ruomin Huang, Hu Ding
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| use RCore instead of Uniform sampling | SVM on Q1 · Home Credit Q1, coreset size 1000 | Approx.: 2.14 -> 0.02 | Improved |
| use RCore instead of Ori-Gon | SVM on Q1 · Home Credit Q1, coreset size 200 | end-to-end runtime (s): 3808 -> 208 | Improved |
| use RCore instead of Ori-Gon | SVM on Q1 · Home Credit Q1, coreset size 200 | Approx.: 1.41 -> 0.92 | Improved |
| use Uniform instead of RCore | SVM on Q1 · Home Credit Q1, coreset size 200 | end-to-end runtime (s): 208 -> 34 | Improved |
| increase coreset size from 200 to 1000 (ablation) | RCore, SVM on Q1 · Home Credit Q1 | Approx.: 0.92 -> 0.02 | Improved |
| increase coreset size from 200 to 1000 (ablation) | RCore, SVM on Q1 · Home Credit Q1 | end-to-end runtime (s): 208 -> 531 | Hurt |
| increase coreset size from 200 to 1000 (ablation) | Uniform, SVM on Q1 · Home Credit Q1 | Approx.: 2.22 -> 2.14 | No clear effect |
| use RCore instead of Uniform sampling | logistic regression on Q1 · Home Credit Q1, coreset size 200 | Approx.: 1.26 -> 0.43 | Improved |
| use RCore instead of Uniform sampling | SVM on Q2 · Home Credit Q2, coreset size 200 | Loss: 1.09\pm0.21 -> 0.40\pm0.18 | Improved |
| use RCore instead of Uniform sampling | logistic regression on Q2 · Home Credit Q2, coreset size 200 | Loss: 6.41\pm5.60 -> 4.13\pm1.70 | Improved |
Closest papers by meaning
- Universal Weak Coreset (AAAI 2024 · similarity 0.86)
- Beyond Worst-Case Coreset Bounds for $k$-Clustering via Determinantal Sampling (NeurIPS 2026 · similarity 0.84)
- Coresets for Clustering Under Stochastic Noise (NeurIPS 2025 · similarity 0.83)
- Improved Coresets for Vertical Federated Learning: Regularized Linear and Logistic Regressions (ICML 2025 · similarity 0.83)
- Coreset for Robust Geometric Median: Eliminating Size Dependency on Outliers (NeurIPS 2025 · similarity 0.82)
- Position: Relational Deep Learning - Graph Representation Learning on Relational Databases (ICML 2024 · similarity 0.82)
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.
