Research map / Probabilistic and scientific modeling / Causal discovery
Counterfactual Fairness with Disentangled Causal Effect Variational Autoencoder
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 |
|---|---|---|---|
| Disentangle exogenous uncertainty into intervention-caused and intervention-correlated latent variables | Causal effect estimation on UCI Adult · UCI Adult | CE error: .1524 ± .0618 -> .0923 ± .0071 | Helped |
| Disentangle exogenous uncertainty into intervention-caused and intervention-correlated latent variables | Causal effect estimation on UCI Adult · UCI Adult | Total effect: .1959 ± .0140 -> .1831 ± .0011 | Mixed |
| Disentangle exogenous uncertainty into intervention-caused and intervention-correlated latent variables | Fair classification data generation · UCI Adult | LR accuracy: .7805 ± .0220 -> .8095 ± .0050 | Helped |
| Disentangle exogenous uncertainty into intervention-caused and intervention-correlated latent variables | Fair classification data generation · UCI Adult | SVM accuracy: .8126 ± .0026 -> .7995 ± .0003 | Hurt |
| Generate counterfactual images while preserving the inferred identity-related latent information | CelebA Mustache image generation · CelebA Mustache (Real) | Identity preserving (IP): 0.29 ± 0.04 -> 0.33 ± 0.02 | Helped |
| Generate counterfactual images while preserving the inferred identity-related latent information | CelebA Mustache image generation · CelebA Mustache (Pair) | Identity preserving (IP): 0.75 ± 0.07 -> 0.98 ± 0.01 | Helped |
| Use a two-latent disentanglement rather than a single shared latent | DCEVAE counterfactual image generation · CelebA Mustache | Preservation of attributes unrelated to intervention | Helped |
| Add counterfactual fairness regularization | DCEVAE fair classification · UCI Adult | Total effect and average counterfactual effect | Helped |
Closest papers by meaning
- Causal Representation Learning via Counterfactual Intervention (AAAI 2024 · similarity 0.89)
- Counterfactual Generative Modeling with Variational Causal Inference (ICLR 2025 · similarity 0.89)
- Towards counterfactual fairness through auxiliary variables (ICLR 2025 · similarity 0.87)
- Towards Characterizing Domain Counterfactuals for Invertible Latent Causal Models (ICLR 2024 · similarity 0.87)
- Causal Inference with Conditional Front-Door Adjustment and Identifiable Variational Autoencoder (ICLR 2024 · similarity 0.87)
- Interventional Fairness on Partially Known Causal Graphs: A Constrained Optimization Approach (ICLR 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.