Research map / Label-efficient and robust learning / Recognition and long-tail
On the Fairness of Disentangled Representations
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 |
|---|---|---|---|
| Use a more disentangled representation, especially one with higher DCI Disentanglement | Downstream prediction models trained on learned representations · Seven datasets | unfairness (total variation) | Helped |
| Use higher BetaVAE, FactorVAE, MIG, or SAP disentanglement scores | Downstream prediction models trained on learned representations · Seven datasets | unfairness (total variation) | Helped |
| Use higher Modularity | Downstream prediction models trained on learned representations · Seven datasets | unfairness (total variation) | No clear effect |
| Increase disentanglement while adjusting for downstream performance | Downstream prediction models trained on learned representations · Most datasets | adjusted unfairness | Helped |
| Use adjusted Modularity, or adjusted BetaVAE and FactorVAE on Shapes3D | Downstream prediction models trained on learned representations · Shapes3D | adjusted unfairness | No clear effect |
| Use adjusted MIG, DCI Disentanglement, Modularity, or SAP | Downstream prediction models trained on learned representations · SmallNORB | adjusted unfairness | No clear effect |
| Select a representation by highest test accuracy rather than choosing a random representation | GBT10000 downstream classifiers over representations · Sampled dataset, seed, target and sensitive-factor tasks | fairness (lower unfairness): 84.2% | Helped |
Closest papers by meaning
- FADES: Fair Disentanglement with Sensitive Relevance (CVPR 2024 · similarity 0.90)
- Revisiting Disentanglement in Downstream Tasks: A Study on Its Necessity for Abstract Visual Reasoning (AAAI 2024 · similarity 0.89)
- $\alpha$TC-VAE: On the relationship between Disentanglement and Diversity (ICLR 2024 · similarity 0.88)
- Disentangled Representation Learning in Non-Markovian Causal Systems (NeurIPS 2024 · similarity 0.88)
- Disentangling Representations through Multi-task Learning (ICLR 2025 · similarity 0.88)
- Disentangled Representation Learning via Modular Compositional Bias (NeurIPS 2025 · similarity 0.87)
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.