Research map / Probabilistic and scientific modeling / Variational and generative sampling
CAD-VAE: Leveraging Correlation-Aware Latents for Comprehensive Fair Disentanglement
Chenrui Ma, Xi Xiao, Tianyang Wang, Xiao Wang, Yanning Shen
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 |
|---|---|---|---|
| CAD-VAE vs FADES | CAD-VAE · CelebA | accuracy: 0.918 -> 0.939 | Improved |
| CAD-VAE vs FADES | CAD-VAE · UTKFace | DP: 0.139 -> 0.137 | Mixed |
| CAD-VAE vs best baseline | CAD-VAE · Dogs and Cats | DP: 0.038 -> 0.069 | Hurt |
| CAD-VAE vs FairFactorVAE | CAD-VAE · Color bias MNIST (95% bias) | accuracy: 0.807 -> 0.867 | Improved |
| CAD-VAE counterfactual generation vs FADES | CAD-VAE · CelebA | delta FID: 1.167 -> 1.072 | Improved |
| apply CAD-VAE fair latent on CLIP features vs linear probe | CLIP ViT-B/32 · Facet Top-1 | worst-group accuracy: 1.17 -> 69.97 | Improved |
Closest papers by meaning
- FADES: Fair Disentanglement with Sensitive Relevance (CVPR 2024 · similarity 0.88)
- Hyperprior Induced Unsupervised Disentanglement of Latent Representations (AAAI 2019 · similarity 0.88)
- Demystifying Inductive Biases for (Beta-)VAE Based Architectures (ICML 2021 · similarity 0.87)
- Disentangled Representation Learning via Flow Matching (NeurIPS 2026 · similarity 0.86)
- Tripod: Three Complementary Inductive Biases for Disentangled Representation Learning (ICML 2024 · similarity 0.85)
- $\alpha$TC-VAE: On the relationship between Disentanglement and Diversity (ICLR 2024 · similarity 0.85)
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.
