feature importance

Making Sense of Dependence: Efficient Black-box Explanations Using Dependence Measure NeurIPS 2022 Rethinking Attention-Model Explainability through Faithfulness Violation Test ICML 2022 SHAFF: Fast and consistent SHApley eFfect estimates via random Forests AISTATS 2022 Threading the Needle of On and Off-Manifold Value Functions for Shapley Explanations AISTATS 2022 Towards a Unified Framework for Uncertainty-aware Nonlinear Variable Selection with Theoretical Guarantees NeurIPS 2022 Trading Complexity for Sparsity in Random Forest Explanations AAAI 2022 VisFIS: Visual Feature Importance Supervision with Right-for-the-Right-Reason Objectives NeurIPS 2022 What You See is What You Classify: Black Box Attributions NeurIPS 2022 Accurate and Robust Feature Importance Estimation under Distribution Shifts AAAI 2021 An Importance Weighted Feature Selection Stability Measure JMLR 2021 Auditing Black-Box Prediction Models for Data Minimization Compliance NeurIPS 2021 A Unified Taylor Framework for Revisiting Attribution Methods AAAI 2021 Building Reliable Explanations of Unreliable Neural Networks: Locally Smoothing Perspective of Model Interpretation CVPR 2021 Context-Sensitive Temporal Feature Learning for Gait Recognition ICCV 2021 Dissecting the Aero-Acoustic Parameters of Open Articulatory Transitions Interspeech 2021 Does BERT Learn as Humans Perceive? Understanding Linguistic Styles through Lexica EMNLP 2021 Explainable Automated Graph Representation Learning with Hyperparameter Importance ICML 2021 Explaining Deep Neural Network Models with Adversarial Gradient Integration IJCAI 2021 Explaining Time Series Predictions with Dynamic Masks ICML 2021 Feature Importance-Aware Transferable Adversarial Attacks ICCV 2021 FIMAP: Feature Importance by Minimal Adversarial Perturbation AAAI 2021 Have We Learned to Explain?: How Interpretability Methods Can Learn to Encode Predictions in their Interpretations. AISTATS 2021 Invertible Concept-based Explanations for CNN Models with Non-negative Concept Activation Vectors AAAI 2021 Marginal Contribution Feature Importance - an Axiomatic Approach for Explaining Data ICML 2021 Reliable Post hoc Explanations: Modeling Uncertainty in Explainability NeurIPS 2021