Interpretability

SmoothHess: ReLU Network Feature Interactions via Stein's Lemma NeurIPS 2023 Testing the Channels of Convolutional Neural Networks AAAI 2023 This Looks Like Those: Illuminating Prototypical Concepts Using Multiple Visualizations NeurIPS 2023 Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models EMNLP 2023 Towards Better Visualizing the Decision Basis of Networks via Unfold and Conquer Attribution Guidance AAAI 2023 Train Once and Explain Everywhere: Pre-training Interpretable Graph Neural Networks NeurIPS 2023 VISIT: Visualizing and Interpreting the Semantic Information Flow of Transformers EMNLP 2023 B-Cos Networks: Alignment Is All We Need for Interpretability CVPR 2022 DeepVisualInsight: Time-Travelling Visualization for Spatio-Temporal Causality of Deep Classification Training AAAI 2022 Explaining Classes through Stable Word Attributions ACL 2022 Finding Skill Neurons in Pre-trained Transformer-based Language Models EMNLP 2022 Is Attention Explanation? An Introduction to the Debate ACL 2022 On the Pitfalls of Analyzing Individual Neurons in Language Models ICLR 2022 Revisiting Sparse Convolutional Model for Visual Recognition NeurIPS 2022 Tracing and Manipulating intermediate values in Neural Math Problem Solvers EMNLP 2022 Visual Explanations for Convolutional Neural Networks via Latent Traversal of Generative Adversarial Networks (Student Abstract) AAAI 2022 Adaptive Consistency Prior Based Deep Network for Image Denoising CVPR 2021 Analyzing the Source and Target Contributions to Predictions in Neural Machine Translation ACL 2021 Explaining Convolutional Neural Networks through Attribution-Based Input Sampling and Block-Wise Feature Aggregation AAAI 2021 Generating Deep Networks Explanations with Robust Attribution Alignment ACML 2021 HyDRA: Hypergradient Data Relevance Analysis for Interpreting Deep Neural Networks AAAI 2021 Improving Deep Learning Interpretability by Saliency Guided Training NeurIPS 2021 Integrated Directional Gradients: Feature Interaction Attribution for Neural NLP Models ACL 2021 Interpreting Deep Neural Networks with Relative Sectional Propagation by Analyzing Comparative Gradients and Hostile Activations AAAI 2021 Interpreting Multivariate Shapley Interactions in DNNs AAAI 2021