Research map / Learning theory and algorithms / Clustering
Crowdsourced Clustering: Querying Edges vs Triangles
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 |
|---|---|---|---|
| replace random edge queries with random triangle queries at equal budget | clustering pipeline (convex program, k-means, spectral) · Dogs3 real AMT data | VI: 0.5176 -> 0.2279 (convex program) | Helped |
| replace random edge queries with random triangle queries at equal budget | clustering pipeline on Birds5 · Birds5 real AMT data | VI: Convex program 1.0392 -> 0.9135; k-means 1.4504 -> 0.7989; spectral 1.2936 -> 0.8713 but triangle convex 0.9135 vs 0.798 | Mixed |
| triangle queries instead of edge queries (fewer edge errors among revealed edges) | adjacency matrix from crowd answers · Dogs3 and Birds5 | % of edge errors: Dogs3 25.2% -> 19.66%/20%; Birds5 14.82% -> 10.96%/11.4% | Helped |
| triangle queries instead of edge queries | simulated SBM graphs, spectral clustering · simulations varying edge density and K | VI: n/a (curves) | Helped |
| triangle queries instead of edge queries in Program 4.1 recovery | convex adjacency recovery · simulated SBM n=600, K=3 | fraction of entries in error: n/a (curves) | Helped |
| triangle queries with equal number of queries as edges (TE, same edge count) vs edges | spectral clustering simulations · simulated SBM | VI: n/a | Mixed |
Closest papers by meaning
- Clustering with Noisy Queries (NeurIPS 2017 · similarity 0.89)
- Clustering Small Samples With Quality Guarantees: Adaptivity With One2all PPS (AAAI 2018 · similarity 0.87)
- Semi-crowdsourced Clustering with Deep Generative Models (NeurIPS 2018 · similarity 0.86)
- Relative Error Fair Clustering in the Weak-Strong Oracle Model (ICML 2025 · similarity 0.85)
- Hierarchical Overlapping Clustering on Graphs: Cost Function, Algorithm and Scalability (ICML 2025 · similarity 0.84)
- Query-Efficient Correlation Clustering with Noisy Oracle (NeurIPS 2024 · similarity 0.84)
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.