Research map / Learning theory and algorithms / Clustering
Active clustering for labeling training data
Quentin Lutz, Elie De Panafieu, Maya Stein, Alex Scott
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 chordal queries instead of a non-chordal query | Active clustering · Uniform random partitions, illustrative query-tree example | average number of queries: 13/5 -> 12/5 | Improved |
| Constrain the algorithm to make chordal queries | Active clustering · Uniform random partitions | average number of queries | Improved |
| Compare new items to discovered blocks in decreasing order of size | Clique algorithm · Random partition with fixed class probabilities | expected number of queries: n-k+\sum_{i<j}f(p_i,p_j)n vs. \sum_{i=1}^k ip_in | Improved |
| Use the random algorithm rather than the clique algorithm | Active clustering · Random partition with k equally likely classes | expected number of queries: (k+1)n/2 vs. k(n-1) | Hurt |
Closest papers by meaning
- Clustering with Same-Cluster Queries (NeurIPS 2016 · similarity 0.88)
- Improved Learning-augmented Algorithms for k-means and k-medians Clustering (ICLR 2023 · similarity 0.87)
- Agnostic Multi-Group Active Learning (NeurIPS 2023 · similarity 0.87)
- Non-Uniform Subset Selection for Active Learning in Structured Data (CVPR 2017 · similarity 0.87)
- Labels, Information, and Computation: Efficient Learning Using Sufficient Labels (JMLR 2023 · similarity 0.87)
- Active Classification with Few Queries under Misspecification (NeurIPS 2024 · similarity 0.86)
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.
