Research map / Learning theory and algorithms / Prediction and decision losses
Interpretable by Design: Learning Predictors by Composing Interpretable Queries
Aditya Chattopadhyay, Stewart Slocum, Benjamin D. Haeffele, René Vidal, Donald Geman
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 IP generative posterior over query-answers instead of CART decision tree on same queries | Information Pursuit · MNIST | accuracy: 90.23% -> 96.78% | Improved |
| use IP instead of decision tree | Information Pursuit · HuffPost | accuracy: 63.00% -> 71.21% | Improved |
| stop IP early (about 2% of queries) versus asking all queries (MAP using Q) (ablation) | Information Pursuit · MNIST | accuracy: 99.05% -> 96.78% | Hurt |
| restrict black-box model to interpretable query features | Black-box · Fashion-MNIST | accuracy: 96.70% -> 88.43% | Hurt |
| use IP explanations instead of Integrated Gradients top patches | Information Pursuit · MNIST | MAP accuracy: 78.48% -> 96.78% | Improved |
| use IP explanations instead of DeepSHAP | Information Pursuit · MNIST | MAP accuracy: 87.98% -> 96.78% | Improved |
| use IP explanations instead of DeepSHAP | Information Pursuit · Fashion-MNIST | MAP accuracy: 88.36% -> 85.60% | Hurt |
| use IP explanations instead of Integrated Gradients (absolute) | Information Pursuit · KMNIST | MAP accuracy: 84.72% -> 91.02% | Improved |
| increase patch size from 1x1 to 3x3 (ablation) | Information Pursuit · MNIST | avg queries to 99% confidence: 21.1 -> 5.2 | Improved |
| increase patch size from 3x3 to 4x4 (ablation) | Information Pursuit · MNIST | avg pixels used: 54.7 pixels for 4x4 vs 21.1 for 1x1 | Hurt |
| add query set complexity (MNIST to FashionMNIST) | Information Pursuit · 3x3 patch queries | avg queries: 5.2 -> 14.5 | Hurt |
Closest papers by meaning
- Enhancing Performance of Explainable AI Models with Constrained Concept Refinement (ICML 2025 · similarity 0.86)
- From Black-box to Causal-box: Towards Building More Interpretable Models (NeurIPS 2025 · similarity 0.86)
- Intrinsic User-Centric Interpretability through Global Mixture of Experts (ICLR 2025 · similarity 0.85)
- Local vs. Global Interpretability: A Computational Complexity Perspective (ICML 2024 · similarity 0.85)
- Explainable Neural Networks with Guarantee: A Sparse Estimation Approach (AAAI 2025 · similarity 0.84)
- Large Language Models are Interpretable Learners (ICLR 2025 · similarity 0.84)
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.
