Latest Research in Explainable Artificial Intelligence (XAI)

Top Research Topics in Explainable Artificial Intelligence (XAI)

• Machine Learning — 11 papers
• Machine Learning — 4 papers
• Methodology — 3 papers
• Explainable Artificial Intelligence (XAI) — 2 papers
• Statistics Theory — 2 papers
• Stochastic Gradient Optimization Techniques — 2 papers
• Machine Learning and ELM — 1 papers
• Theoretical Economics — 1 papers
• Solar and Stellar Astrophysics — 1 papers
• Statistical Mechanics — 1 papers

Highest-Cited Papers

1. Conformal Policy Learning with Distribution-Free Safety Guarantees
2. Multi-Attribute Preferences: A Transfer Learning Approach
3. Learned Look-Ahead Splitting Rule for CART
4. Compute-Optimal Pretrain--Fine-tune in Ridge Gradient Descent
5. Robust Functional Basis Neural Network Method With the Normalization
6. Proper Calibeating
7. Noise-Adaptive Conformal Classification with Marginal Coverage
8. Generative Learner for Distributional Causal Effects
9. L-Lipschitz Gershgorin ResNet Network
10. Local Robustness Quantification for Naive Bayes Classifiers and Generative Forests: a General Approach
11. A Farewell to the Bias-Variance Tradeoff? An Overview of the Theory of Overparameterized Machine Learning
12. Speed Limit for Information Acquisition in Stochastic Learning Dynamics
13. An Identifiability Theory of Masked Prediction: Mode Blindness and Mask Schedules
14. Critical initialization destabilizes higher input derivatives in wide scalar-input networks
15. Original Sin: Hardware Sovereignty and the Physical Limits of Artificial Intelligence
16. Class-Conditional Conformal Prediction with Uncertainty-Triggered Selective Explainability for HighStakes Imbalanced Tabular Decisions
17. Stability and Generalization of Straight-Through Estimators for Training Two-Layer Quantized Neural Networks
18. Beyond Causal Identifiability: Order-Indexed Ambiguity, Decision Sufficiency, and Consequence-Directed Intervention Design
19. Boosting Data Augmentation with Stochastic Weight Averaging
20. Correlated initialization of deep residual networks