integrated gradient

Explaining Translationese: why are Neural Classifiers Better and what do they Learn? EMNLP 2022 ExplainIt!: A Tool for Computing Robust Attributions of DNNs IJCAI 2022 Exploiting the Relationship Between Kendall's Rank Correlation and Cosine Similarity for Attribution Protection NeurIPS 2022 Minimally-Supervised Relation Induction from Pre-trained Language Model NAACL 2022 Robust Models Are More Interpretable Because Attributions Look Normal ICML 2022 Shaping Noise for Robust Attributions in Neural Stochastic Differential Equations AAAI 2022 SInGE: Sparsity via Integrated Gradients Estimation of Neuron Relevance NeurIPS 2022 Transferable Adversarial Attack based on Integrated Gradients ICLR 2022 Zero-shot Code-Mixed Offensive Span Identification through Rationale Extraction ACL 2022 Discretized Integrated Gradients for Explaining Language Models EMNLP 2021 Explaining Deep Neural Network Models with Adversarial Gradient Integration IJCAI 2021 Explaining Explanations: Axiomatic Feature Interactions for Deep Networks JMLR 2021 Guided Integrated Gradients: An Adaptive Path Method for Removing Noise CVPR 2021 Interpreting Super-Resolution Networks With Local Attribution Maps CVPR 2021 LRG at SemEval-2021 Task 4: Improving Reading Comprehension with Abstract Words using Augmentation, Linguistic Features and Voting SemEval 2021 Perturbing Inputs for Fragile Interpretations in Deep Natural Language Processing EMNLP 2021 Scaling Symbolic Methods using Gradients for Neural Model Explanation ICLR 2021 To what extent do human explanations of model behavior align with actual model behavior? EMNLP 2021 What does LIME really see in images? ICML 2021 Attribution in Scale and Space CVPR 2020 Concise Explanations of Neural Networks using Adversarial Training ICML 2020 Interpretable, Multidimensional, Multimodal Anomaly Detection with Negative Sampling for Detection of Device Failure ICML 2020 Q-value Path Decomposition for Deep Multiagent Reinforcement Learning ICML 2020 Towards Interpreting BERT for Reading Comprehension Based QA EMNLP 2020 Visualizing Deep Networks by Optimizing with Integrated Gradients AAAI 2020