Research map / Learning theory and algorithms / Fairness
RECAST: Model Reconstruction via Counterfactual-Aware Wasserstein Geometry under Limited Data
Xuan Zhao, Lena Krieger, Zhuo Cao, Arya Bangun, Hanno Scharr, Ira Assent
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 |
|---|---|---|---|
| add RECAST (Wasserstein barycentric prototypes with soft CFs) over SAMPLES (CFs as full labeled samples) | SAMPLES / MLP target · COMPAS (query size 100) | fidelity: 0.415 -> 0.855 | Improved |
| use RECAST instead of CCA | CCA / DT target · COMPAS (query size 100) | fidelity: 0.657 -> 0.869 | Improved |
| use RECAST instead of SAMPLES on logistic regression targets | SAMPLES / LR target · Adult Income (query size 100) | fidelity: 0.909 -> 0.913 | No clear effect |
| use RECAST instead of CCA on a Housing MLP target | CCA / MLP target · California Housing (query size 100) | fidelity: 0.716 -> 0.712 | No clear effect |
| use RECAST instead of TRA (which assumes a decision tree target) | TRA / DT target · Adult Income (query size 100) | fidelity: 0.842 -> 0.894 | Improved |
| use RECAST instead of SAMPLES when CFs come from C-CHVAE | SAMPLES / MLP target · Adult Income (CF generator C-CHVAE) | fidelity: 0.357 -> 0.923 | Improved |
| use RECAST instead of SAMPLES when CFs come from DiCE | SAMPLES / MLP target · Adult Income (CF generator DiCE) | fidelity: 0.933 -> 0.923 | Hurt |
| use RECAST instead of baselines under CF generator variation | SAMPLES and CCA · Adult Income (varying CF generators) | fidelity variability | Improved |
| use RECAST under additive test noise (tau up to 0.4) | SAMPLES and CCA · Adult Income, full and near-threshold sets | fidelity drop | Improved |
| use RECAST when the query budget is small (25 to 400) | SAMPLES and CCA · Adult/COMPAS/HELOC/Housing | fidelity | Improved |
| increase query budget until supervised no-CF reconstruction catches up | RECAST vs no-CF baseline · query-budget sweep | fidelity advantage | Mixed |
| use RECAST fairness diagnostics (TIDP/TIEO) on reconstructed model | SAMPLES and CCA · fairness diagnostic error under noise | absolute diagnostic difference | Improved |
Closest papers by meaning
- Model Reconstruction Using Counterfactual Explanations: A Perspective From Polytope Theory (NeurIPS 2024 · similarity 0.89)
- Counterfactual Metarules for Local and Global Recourse (ICML 2024 · similarity 0.85)
- Faithful Model Explanations through Energy-Constrained Conformal Counterfactuals (AAAI 2024 · similarity 0.85)
- Geometry of Relaxed Fair Regression: A Unified Framework for Aware and Unaware Settings (NeurIPS 2026 · similarity 0.85)
- On the Burden of Achieving Fairness in Conformal Prediction (NeurIPS 2026 · similarity 0.85)
- ElliCE: Efficient and Provably Robust Algorithmic Recourse via the Rashomon Sets (NeurIPS 2025 · 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.
