conftrace_

model interpretation

93 papers

Explore in graph

Co-occurring keywords

neural network (6616) model interpretability (519) feature attribution (280) shapley value (206) influence function (143) feature importance (139) adversarial attack (1621) saliency map (125) deep learning (2118) explainable ai (480)

Papers

NeuroX Library for Neuron Analysis of Deep NLP Models ACL 2023
Use perturbations when learning from explanations NIPS 2023
Rethinking Interpretation: Input-Agnostic Saliency Mapping of Deep Visual Classifiers AAAI 2023
From Shapley Values to Generalized Additive Models and back AISTATS 2023
Learning with Explanation Constraints NIPS 2023
WeightedSHAP: analyzing and improving Shapley based feature attributions NIPS 2022
Learning by Interpreting IJCAI 2022
Consistent Explanations by Contrastive Learning CVPR 2022
Reliable Visualization for Deep Speaker Recognition INTERSPEECH 2022
Do Charge Prediction Models Learn Legal Theory? EMNLP 2022
InterpretDL: Explaining Deep Models in PaddlePaddle JMLR 2022
TransBoost: A Boosting-Tree Kernel Transfer Learning Algorithm for Improving Financial Inclusion AAAI 2022
An Adversarial Framework for Generating Unseen Images by Activation Maximization AAAI 2022
Scaling Up Influence Functions AAAI 2022
On the Sensitivity and Stability of Model Interpretations in NLP ACL 2022
How (Un)Faithful is Attention? EMNLP 2022
Improving Large-Scale Conversational Assistants using Model Interpretation based Training Sample Selection EMNLP 2022
RKHS-SHAP: Shapley Values for Kernel Methods NIPS 2022
If Influence Functions are the Answer, Then What is the Question? NIPS 2022
Logic Rule Guided Attribution with Dynamic Ablation AAAI 2022
Do Feature Attribution Methods Correctly Attribute Features? AAAI 2022
Predicting Fine-Tuning Performance with Probing EMNLP 2022
PlanT: Explainable Planning Transformers via Object-Level Representations CORL 2022
Explaining Contextualization in Language Models using Visual Analytics ACL 2021
Explaining Time Series Predictions with Dynamic Masks ICML 2021