Interpretability

Biologically Inspired Mechanisms for Adversarial Robustness NeurIPS 2020 Black-Box Adversarial Attack with Transferable Model-based Embedding ICLR 2020 BLEURT: Learning Robust Metrics for Text Generation ACL 2020 Blindly Assess Image Quality in the Wild Guided by a Self-Adaptive Hyper Network CVPR 2020 BlockGAN: Learning 3D Object-aware Scene Representations from Unlabelled Images NeurIPS 2020 Boosting the Transferability of Adversarial Samples via Attention CVPR 2020 Born-Again Tree Ensembles ICML 2020 Bounding boxes for weakly supervised segmentation: Global constraints get close to full supervision MIDL 2020 Brain Metastasis Segmentation Network Trained with Robustness to Annotations with Multiple False Negatives MIDL 2020 Capturing the Style of Fake News AAAI 2020 Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Models NeurIPS 2020 Certifai: A Toolkit for Building Trust in AI Systems IJCAI 2020 Certifiably Adversarially Robust Detection of Out-of-Distribution Data NeurIPS 2020 Certified Monotonic Neural Networks NeurIPS 2020 Certified Robustness of Graph Convolution Networks for Graph Classification under Topological Attacks NeurIPS 2020 Clinical-Coder: Assigning Interpretable ICD-10 Codes to Chinese Clinical Notes ACL 2020 Closed Loop Neural-Symbolic Learning via Integrating Neural Perception, Grammar Parsing, and Symbolic Reasoning ICML 2020 CoCoX: Generating Conceptual and Counterfactual Explanations via Fault-Lines AAAI 2020 Cold-Start and Interpretability: Turning Regular Expressions into Trainable Recurrent Neural Networks EMNLP 2020 Compositional Generalization via Neural-Symbolic Stack Machines NeurIPS 2020 Concept Bottleneck Models ICML 2020 Concise Explanations of Neural Networks using Adversarial Training ICML 2020 Confidence-Aware Learning for Deep Neural Networks ICML 2020 Considering Likelihood in NLP Classification Explanations with Occlusion and Language Modeling ACL 2020 Consistent feature selection for analytic deep neural networks NeurIPS 2020