A transformer model guided by a causal graph prior achieves state-of-the-art anomaly detection and root-cause attribution on ASD and SMD benchmarks by restricting main predictions to graph-supported causes while using an isolated shadow path for residual correlations.
Model selection and estimation in regression with grouped variables
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.LG 3years
2026 3representative citing papers
An explainability-aware L0 penalty yields coherent counterfactual edits, and the same geometry defines a Tolerance-Region Confusion Matrix that quantifies class-to-class fragility under interpretable perturbations.
Introduces Learnable Gate (LG) methods that improve group-level sparsity in counterfactual explanations for rehabilitation IMU data while preserving validity and smoothness compared to channel-level baselines.
citing papers explorer
-
Causally-Constrained Probabilistic Forecasting for Time-Series Anomaly Detection
A transformer model guided by a causal graph prior achieves state-of-the-art anomaly detection and root-cause attribution on ASD and SMD benchmarks by restricting main predictions to graph-supported causes while using an isolated shadow path for residual correlations.
-
Optimized Instance Alteration for Explaining and Assessing Robustness of Classifiers
An explainability-aware L0 penalty yields coherent counterfactual edits, and the same geometry defines a Tolerance-Region Confusion Matrix that quantifies class-to-class fragility under interpretable perturbations.
-
Adaptive Group-Based Counterfactual Explanations for Time-Series Rehabilitation Data
Introduces Learnable Gate (LG) methods that improve group-level sparsity in counterfactual explanations for rehabilitation IMU data while preserving validity and smoothness compared to channel-level baselines.