Research map / Label-efficient and robust learning / Recognition and long-tail
Learning Global Probabilistic Explanations
Frederic Koriche, Louenas Bounia
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Defines global probabilistic explanations as small feature subsets whose relevance to a black-box classifier's behavior is measured probabilistically across the input distribution.
Problem
Explaining the overall behavior of complex black-box classifiers across the input distribution, beyond individual local explanations.
Approach
Defines a global probabilistic explanation as a small feature subset K whose relevance is measured over the data distribution, rather than per-instance attributions.
Closest papers by meaning
- Unifying Formal Explanations: A Complexity-Theoretic Perspective (ICLR 2026 · similarity 0.90)
- Computing Probabilistic Explanations for ML Models: Fixed-Parameter Algorithms (AAAI 2026 · similarity 0.88)
- Trust Regions for Explanations via Black-Box Probabilistic Certification (ICML 2024 · similarity 0.87)
- Efficient and Accurate Explanation Estimation with Distribution Compression (ICLR 2025 · similarity 0.87)
- Selective Explanations (NeurIPS 2024 · similarity 0.86)
- Local vs. Global Interpretability: A Computational Complexity Perspective (ICML 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.
