Research map / Learning theory and algorithms / Clustering
Deep Fair Clustering for Visual Learning
Check 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 |
|---|---|---|---|
| Use DFC instead of DAC | Fair clustering on MNIST-USPS · MNIST-USPS | Accuracy: 0.757 -> 0.825 | Helped |
| Use DFC instead of ScFC | Fair clustering on MNIST-USPS · MNIST-USPS | Balance: 0.120 -> 0.067 | Hurt |
| Use DFC instead of DEC | Fair clustering on Color Reverse MNIST · Color Reverse MNIST | NMI: 0.480 -> 0.679 | Helped |
| Use DFC instead of ScFC | Fair clustering on Color Reverse MNIST · Color Reverse MNIST | Balance: 1.000 -> 0.763 | Hurt |
| Use DFC instead of ClGAN | Fair clustering on MTFL · MTFL | Accuracy: 0.727 -> 0.719 | Hurt |
| Use DFC instead of FAlg | Fair clustering on MTFL · MTFL | NMI: 0.181 -> 0.190 | Helped |
| Use DFC instead of ScFC | Fair clustering on MTFL · MTFL | Balance: 1.000 -> 0.986 | Hurt |
| Use DFC instead of FAlg | Fair clustering on Office-31 · Office-31 | Accuracy: 0.689 -> 0.692 | Helped |
| Use DFC instead of FAlg | Fair clustering on Office-31 · Office-31 | NMI: 0.713 -> 0.718 | Helped |
| Use DFC instead of ScFC | Fair clustering on Office-31 · Office-31 | Balance: 0.273 -> 0.117 | Hurt |
| Remove structural preservation loss (set αs=0) (ablation) | DFC · Fair clustering; parameter analysis | NMI | Hurt |
| Increase αs (ablation) | DFC · Fair clustering; parameter analysis | NMI | Helped |
Closest papers by meaning
- FairGC: Fostering Individual and Group Fairness for Deep Graph Clustering (AAAI 2026 · similarity 0.90)
- Deep Fair Multi-View Clustering with Attention KAN (CVPR 2025 · similarity 0.89)
- Fair Clustering Through Fairlets (NeurIPS 2017 · similarity 0.88)
- Generalizing Fair Clustering to Multiple Groups: Algorithms and Applications (AAAI 2026 · similarity 0.88)
- Fair Clustering via Alignment (ICML 2025 · similarity 0.86)
- Towards Fairer Centroids in K-means Clustering (AAAI 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.