← Core Methods
Machine Learning › Core Methods ›

Interpretability

349 directly classified papers

Papers per year

Papers

Using Shapley Values and Variational Autoencoders to Explain Predictive Models with Dependent Mixed Features JMLR 2022
The Architectural Bottleneck Principle EMNLP 2022
WeightedSHAP: analyzing and improving Shapley based feature attributions NIPS 2022
VICE: Variational Interpretable Concept Embeddings NIPS 2022
Distilled Gradient Aggregation: Purify Features for Input Attribution in the Deep Neural Network NIPS 2022
Exploring the Latent Space of Autoencoders with Interventional Assays NIPS 2022
Additive MIL: Intrinsically Interpretable Multiple Instance Learning for Pathology NIPS 2022
Pre-activation Distributions Expose Backdoor Neurons NIPS 2022
SkinCon: A skin disease dataset densely annotated by domain experts for fine-grained debugging and analysis NIPS 2022
If Influence Functions are the Answer, Then What is the Question? NIPS 2022
RankFeat: Rank-1 Feature Removal for Out-of-distribution Detection NIPS 2022
On the Interpretability of Regularisation for Neural Networks Through Model Gradient Similarity NIPS 2022
Where do Models go Wrong? Parameter-Space Saliency Maps for Explainability NIPS 2022
Sparse Interaction Additive Networks via Feature Interaction Detection and Sparse Selection NIPS 2022
RKHS-SHAP: Shapley Values for Kernel Methods NIPS 2022
Scalable Interpretability via Polynomials NIPS 2022
Listen to Interpret: Post-hoc Interpretability for Audio Networks with NMF NIPS 2022
Explainable Planner Selection for Classical Planning AAAI 2022
Towards Disentangling Information Paths with Coded ResNeXt NIPS 2022
Neural Basis Models for Interpretability NIPS 2022
Consistent Sufficient Explanations and Minimal Local Rules for explaining the decision of any classifier or regressor NIPS 2022
A Comparative Study of Faithfulness Metrics for Model Interpretability Methods ACL 2022
Visualizing the Relationship Between Encoded Linguistic Information and Task Performance ACL 2022
Interpretable Research Replication Prediction via Variational Contextual Consistency Sentence Masking ACL 2022
On the data requirements of probing ACL 2022