Research map / Learning theory and algorithms / Prediction and decision losses
Very Fast, Approximate Counterfactual Explanations for Decision Forests
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 |
|---|---|---|---|
| Search forest regions populated by data points instead of searching only dataset instances | LIRE with axis-aligned Random Forests · MNIST | normalized ℓ2 distance: 1.41 -> 1.00 | Helped |
| Search forest regions populated by data points instead of searching only dataset instances | LIRE with axis-aligned Random Forests · Swarm | normalized ℓ2 distance: 11.21 -> 1.00 | Helped |
| Search forest regions populated by data points instead of searching only dataset instances | LIRE with oblique Random Forests · MNIST | normalized ℓ2 distance: 3.03 -> 1.00 | Helped |
| Search forest regions populated by data points instead of searching only dataset instances | LIRE with Random Forest regression · CT slice | normalized ℓ2 distance: 2.01 -> 1.00 | Helped |
| Restrict counterfactual search to live regions rather than all nonempty regions | LIRE · Small forest problems with exact search | distance to source instance | Hurt |
| Use live-region search rather than direct dataset-point search | LIRE · Classification and regression datasets | runtime | Mixed |
| Use LIRE rather than OCEAN | Axis-aligned Random Forest counterfactuals · MNIST | runtime (s): 2×10^{-1} vs timeout | Helped |
| Use LIRE rather than Feature Tweak | Axis-aligned Random Forest counterfactuals · MNIST | feasible counterfactual rate: 0% vs -- | Helped |
Closest papers by meaning
- Counterfactual Explanations for Oblique Decision Trees:Exact, Efficient Algorithms (AAAI 2021 · similarity 0.90)
- Optimal Counterfactual Explanations in Tree Ensembles (ICML 2021 · similarity 0.90)
- Counterfactual Maps: What They Are and How to Find Them (NeurIPS 2026 · similarity 0.88)
- A General Search-Based Framework for Generating Textual Counterfactual Explanations (AAAI 2024 · similarity 0.86)
- Generating Likely Counterfactuals Using Sum-Product Networks (ICLR 2025 · similarity 0.85)
- Near-Optimal Decision Trees in a SPLIT Second (ICML 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.