conftrace_

model explanation

155 papers

Explore in graph

Co-occurring keywords

feature attribution (280) model interpretability (519) shapley value (206) feature importance (139) explainable ai (480) black-box model (90) text classification (6793) graph neural network (3962) attention mechanism (4001) neural network (6616)

Papers

On Explainability of Graph Neural Networks via Subgraph Explorations ICML 2021
Improving the Faithfulness of Attention-based Explanations with Task-specific Information for Text Classification IJCNLP 2021
Perturbing Inputs for Fragile Interpretations in Deep Natural Language Processing EMNLP 2021
Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models ACL 2021
Towards Fair and Transparent Algorithmic Systems IJCAI 2021
A Unified Taylor Framework for Revisiting Attribution Methods AAAI 2021
On Explaining Random Forests with SAT IJCAI 2021
Explaining Explanations: Axiomatic Feature Interactions for Deep Networks JMLR 2021
Provably efficient, succinct, and precise explanations NIPS 2021
Thermostat: A Large Collection of NLP Model Explanations and Analysis Tools EMNLP 2021
Have We Learned to Explain?: How Interpretability Methods Can Learn to Encode Predictions in their Interpretations. AISTATS 2021
Understanding Interlocking Dynamics of Cooperative Rationalization NIPS 2021
Characterizing the risk of fairwashing NIPS 2021
Decision-Focused Summarization EMNLP 2021
Explanations for Occluded Images ICCV 2021
Probabilistic Sufficient Explanations IJCAI 2021
BERT meets Shapley: Extending SHAP Explanations to Transformer-based Classifiers EACL 2021
Learning to Explain: Generating Stable Explanations Fast ACL 2021
Right for Better Reasons: Training Differentiable Models by Constraining their Influence Functions AAAI 2021
Explaining Time Series Predictions with Dynamic Masks ICML 2021
Explanation Consistency Training: Facilitating Consistency-Based Semi-Supervised Learning with Interpretability AAAI 2021
Evaluating and Aggregating Feature-based Model Explanations IJCAI 2020
Relation Extraction with Explanation ACL 2020
Staying True to Your Word: (How) Can Attention Become Explanation? ACL 2020
Evaluating Attribution Methods using White-Box LSTMs EMNLP 2020