Interpretability

Is Multi-Hop Reasoning Really Explainable? Towards Benchmarking Reasoning Interpretability EMNLP 2021 Iterative Bounding MDPs: Learning Interpretable Policies via Non-Interpretable Methods AAAI 2021 Learning Decision Trees Recurrently Through Communication CVPR 2021 Learning to Explain: Generating Stable Explanations Fast ACL 2021 Learning Tree Interpretation from Object Representation for Deep Reinforcement Learning NeurIPS 2021 Measuring Association Between Labels and Free-Text Rationales EMNLP 2021 MMIM: An Interpretable Regularization Method for Neural Networks (Student Abstract) AAAI 2021 On Generating Plausible Counterfactual and Semi-Factual Explanations for Deep Learning AAAI 2021 On Locality of Local Explanation Models NeurIPS 2021 On the Tractability of SHAP Explanations AAAI 2021 Quantifying Explainers of Graph Neural Networks in Computational Pathology CVPR 2021 Reasoning-Based Learning of Interpretable ML Models IJCAI 2021 Relevance-CAM: Your Model Already Knows Where To Look CVPR 2021 Representer Point Selection via Local Jacobian Expansion for Post-hoc Classifier Explanation of Deep Neural Networks and Ensemble Models NeurIPS 2021 Reverse engineering recurrent neural networks with Jacobian switching linear dynamical systems NeurIPS 2021 Scalable Partial Explainability in Neural Networks via Flexible Activation Functions (Student Abstract) AAAI 2021 Screening Gender Transfer in Neural Machine Translation EMNLP 2021 SELFEXPLAIN: A Self-Explaining Architecture for Neural Text Classifiers EMNLP 2021 “Something Something Hota Hai!” An Explainable Approach towards Sentiment Analysis on Indian Code-Mixed Data EMNLP 2021 Syntactic Perturbations Reveal Representational Correlates of Hierarchical Phrase Structure in Pretrained Language Models ACL 2021 TabNet: Attentive Interpretable Tabular Learning AAAI 2021 The effectiveness of feature attribution methods and its correlation with automatic evaluation scores NeurIPS 2021 The Tractability of SHAP-Score-Based Explanations for Classification over Deterministic and Decomposable Boolean Circuits AAAI 2021 Towards Multi-Grained Explainability for Graph Neural Networks NeurIPS 2021 Towards robust vision by multi-task learning on monkey visual cortex NeurIPS 2021