Research map / Learning theory and algorithms / Clustering
Fair Hierarchical Clustering
Sara Ahmadian, Alessandro Epasto, Marina Knittel, Ravi Kumar, Mohammad Mahdian, Benjamin Moseley, Philip Pham, Sergei Vassilvitskii, Yuyan Wang
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 |
|---|---|---|---|
| Add local-search swaps to the randomly initialized fairlet decomposition (ablation) | Fair hierarchical clustering · CensusGender, CensusRace, BankMarriage, BankAge (1600 samples) | value vs. average-linkage (%): CensusGender: $88.27 \pm 0.40 $ -> $99.55 \pm 0.26 $; CensusRace: $85.00 \pm 0.42$ -> $100.0 \pm 0.21$; BankMarriage: $9 | Improved |
| Add local-search swaps to reduce within-fairlet distance (ablation) | Fairlet decomposition · CensusGender, CensusRace, BankMarriage, BankAge (1600 samples) | fairlet objective ratio: CensusGender: 1.5e-3 -> 8.5e-5; CensusRace: 4.2e-3 -> 1.5e-3; BankMarriage: 1.0e-3 -> 1.3e-4; BankAge: 9.3e-4 -> 1.3e-4 | Improved |
| Use fair hierarchical clustering rather than standard average-linkage | Hierarchical clustering · CensusGender, CensusRace, BankMarriage, BankAge | fairness | Improved |
| Require fairness using fairlets and local-search decomposition | Hierarchical clustering · CensusGender, CensusRace, BankMarriage, BankAge | value vs. average-linkage (%): At 1600 samples: $99.55 \pm 0.26 $, $100.0 \pm 0.21$, $99.59 \pm 0.14$, $99.61 \pm 0.13$ | No clear effect |
Closest papers by meaning
- A Pairwise Fair and Community-preserving Approach to k-Center Clustering (ICML 2020 · similarity 0.86)
- Fair, Polylog-Approximate Low-Cost Hierarchical Clustering (NeurIPS 2023 · similarity 0.86)
- Fair Clustering Through Fairlets (NeurIPS 2017 · similarity 0.86)
- Towards Fairer Centroids in K-means Clustering (AAAI 2024 · similarity 0.83)
- Fair Clustering via Alignment (ICML 2025 · similarity 0.82)
- Proportional Fairness in Non-Centroid Clustering (NeurIPS 2024 · similarity 0.81)
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.
