CUBE: Contrastive Understanding by Balanced Experiments
cs.LG, cs.AI, stat.ML
Submitted: 2025-09-13
Updated: 2026-09-13
Comments: Revised version with expanded theoretical analysis and experiments. 33 pages, including appendices
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- NODE-GAM: Neural Generalized Additive Model for Interpretable Deep Learning
- Statistical Aspects of SHAP: Functional ANOVA for Model Interpretation
- Detecting Statistical Interactions from Neural Network Weights
- Feature Interaction Interpretability: A Case for Explaining Ad-Recommendation Systems via Neural Interaction Detection
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks