Research map / Learning theory and algorithms / Combinatorial and search optimization
Optimal Counterfactual Explanations in Tree Ensembles
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 OCEAN instead of feature tweaking (FT) | Counterfactual search for tree ensembles · Adult, Credit Card Default, COMPAS, German Credit, Online News, Data Phishing, Spambase, Students Performance | l1 distance ratio to optimum: 15.9, 10.2, 4.5, 4.8, 31.7, 1.4; FT found no feasible explanation for SP and ST | Helped |
| Add isolation-forest plausibility constraints (ablation) | OCEAN · Adult, Credit Card Default, COMPAS, German Credit, Online News, Data Phishing, Spambase, Students Performance | plausible explanations (P): 55% -> 100%; 0% -> 100%; 25% -> 100%; 25% -> 100%; 100% -> 100%; 35% -> 100%; 100% -> 100%; 40% -> 100% | Helped |
| Add isolation-forest plausibility constraints (ablation) | OCEAN · Adult, Credit Card Default, COMPAS, German Credit, Online News, Data Phishing, Spambase, Students Performance | explanation cost (C): 0.21 -> 0.40; 0.03 -> 0.56; 0.12 -> 0.57; 0.09 -> 1.13; 0.01 -> 0.01; 0.78 -> 2.40; 0.02 -> 0.02; 1.18 -> 1.63 | Mixed |
| Add isolation-forest plausibility constraints (ablation) | OCEAN · Adult, Credit Card Default, COMPAS, German Credit, Online News, Data Phishing, Spambase, Students Performance | CPU time (s): 0.75 -> 1.82; 0.99 -> 1.54; 0.44 -> 0.85; 0.60 -> 1.71; 1.34 -> 1.64; 0.36 -> 1.81; 2.71 -> 4.43; 0.62 -> 1.36 | Hurt |
| Use OCEAN instead of OAE | Counterfactual search for tree ensembles · Adult, Credit Card Default, German Credit, Online News, Data Phishing, Spambase, Students Performance | CPU time (s): 28.37 -> 1.22; 5.52 -> 1.34; 5.08 -> 1.16; >900 -> 2.97; 0.94 -> 0.52; >900 -> 2.73; 69.64 -> 1.10 | Helped |
| Use OCEAN instead of OAE | Counterfactual search for tree ensembles · COMPAS | CPU time (s): 0.38 -> 0.52 | Hurt |
Closest papers by meaning
- Counterfactual Maps: What They Are and How to Find Them (NeurIPS 2026 · similarity 0.91)
- Tree Ensemble Explainability through the Hoeffding Functional Decomposition and TreeHFD Algorithm (NeurIPS 2025 · similarity 0.87)
- Promoting Counterfactual Robustness through Diversity (AAAI 2024 · similarity 0.86)
- Faithful Model Explanations through Energy-Constrained Conformal Counterfactuals (AAAI 2024 · similarity 0.86)
- A General Search-Based Framework for Generating Textual Counterfactual Explanations (AAAI 2024 · similarity 0.86)
- From Counterfactuals to Trees: Competitive Analysis of Model Extraction Attacks (NeurIPS 2025 · 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.