Research map / Probabilistic and scientific modeling / Causal discovery
SPARC: Scalable Path-Specific Counterfactual Fairness via Causal Conditional Independence
Bowei Tian, Yexiao He, Ziyao Wang, Meng Liu, Yongkai Wu, Ang Li
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 |
|---|---|---|---|
| use SPARC instead of vanilla fine-tuning | ResNet50 · TCGA-LUAD | EOd (x1e-3): 7.21 -> 1.46 | Improved |
| use SPARC instead of vanilla fine-tuning | ResNet50 · MIMIC-CXR | Accuracy (%): 85.46 -> 84.26 | Hurt |
| use SPARC instead of Group-DRO | ResNet50 · CheXpert | EOd (x1e-3): 3.07 -> 1.20 | Improved |
| use ViT backbone instead of ResNet50 (ablation) | SPARC · MIMIC-CXR | Accuracy (%): 84.26 -> 86.95 | Improved |
| use ViT backbone instead of ResNet50 (ablation) | SPARC · MIMIC-CXR | EOp (x1e-2): 2.02 -> 3.35 | Hurt |
| use age (binarized at 60) as sensitive attribute (ablation) | SPARC · MIMIC-CXR | EOd (x1e-3): 9.38 -> 1.45 | Improved |
| increase entropy loss weight alpha from 0 to 4 (ablation) | SPARC · MIMIC | EOd (x1e-3): 2.32 -> 1.13 | Improved |
| increase entropy loss weight alpha from 0 to 4 (ablation) | SPARC · TCGA | EOd (x1e-3): 4.79 -> 1.46 | Improved |
| increase generator loss weight beta from 0 to 4 (ablation) | SPARC · MIMIC | Accuracy (%): 80.69 -> 87.79 | Improved |
| increase generator loss weight beta from 0 to 4 (ablation) | SPARC · MIMIC | EOd (x1e-3): 0.98 -> 5.50 | Hurt |
| increase mask noise strength eta (ablation) | SPARC · MIMIC-CXR | Accuracy (%) | Hurt |
| use SPARC instead of AD on synthetic SCM | SPARC · Synthetic SCM | |IE(S)| preserved: 0.061 -> 0.171 | Improved |
Closest papers by meaning
- Fairness-Accuracy Trade-Offs: A Causal Perspective (AAAI 2025 · similarity 0.87)
- FairPFN: A Tabular Foundation Model for Causal Fairness (ICML 2025 · similarity 0.86)
- Towards counterfactual fairness through auxiliary variables (ICLR 2025 · similarity 0.86)
- Sequential Conditional Transport on Probabilistic Graphs for Interpretable Counterfactual Fairness (AAAI 2025 · similarity 0.86)
- Causal Adversarial Perturbations for Individual Fairness and Robustness in Heterogeneous Data Spaces (AAAI 2024 · similarity 0.86)
- Causal Fairness under Unobserved Confounding: A Neural Sensitivity Framework (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.
