{"url":"/method/interpretability","slug":"interpretability","name":"Interpretability","full_name":"Interpretability","full_name_withheld":false,"description_markdown":null,"description_state":"placeholder","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":"http://arxiv.org/abs/1310.1533v2","title":"CAM: Causal additive models, high-dimensional order search and penalized regression","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Image Models","url":"/methods/category/image-models","pwc_aliases":[]}],"n_papers_tagged":1322,"archive_num_papers":null,"papers_newest_first":[{"paper":null,"title":"A Half-Space Stochastic Projected Gradient Method for Group Sparsity Regularization","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"title":"A self-explanatory method for the black problem on discrimination part of CNN","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"title":"Causal Probabilistic Spatio-temporal Fusion Transformers in Two-sided Ride-Hailing Markets","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"title":"Causal Screening to Interpret Graph Neural Networks","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"title":"DACT-BERT: Increasing the efficiency and interpretability of BERT by using adaptive computation time.","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"title":"Democratizing Evaluation of Deep Model Interpretability through Consensus","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"title":"Exemplary natural images explain CNN activations better than synthetic feature visualizations","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"title":"Generalizing Tree Models for Improving Prediction Accuracy","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"title":"Good for Misconceived Reasons: Revisiting Neural Multimodal Machine Translation","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"title":"Guiding Representation Learning in Deep Generative Models with Policy Gradients","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"title":"Hard Masking for Explaining Graph Neural Networks","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"title":"Interpretability Through Invertibility: A Deep Convolutional Network With Ideal Counterfactuals And Isosurfaces","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"title":"Interpretable Reinforcement Learning With Neural Symbolic Logic","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"title":"Modelling Drug-Target Binding Affinity using a BERT based Graph Neural network","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"title":"Monotonic Kronecker-Factored Lattice","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"title":"NBDT: Neural-Backed Decision Tree","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"title":"Neural Disjunctive Normal Form: Vertically Integrating Logic With Deep Learning For Classification","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"title":"RRL: A Scalable Classifier for Interpretable Rule-Based Representation Learning","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"title":"Structure Controllable Text Generation","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/the-role-of-disentanglement-in-generalisation","title":"The role of Disentanglement in Generalisation","date":"2021-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"title":"Understanding and Leveraging Causal Relations in Deep Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"title":"Variational saliency maps for explaining model's behavior","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"title":"Gender Bias in Multilingual Neural Machine Translation: The Architecture Matters","date":"2020-12-24","arxiv_id":"2012.13176","n_code_links":0,"syntology":null},{"paper":null,"title":"Multi-modal Identification of State-Sponsored Propaganda on Social Media","date":"2020-12-24","arxiv_id":"2012.13042","n_code_links":0,"syntology":null},{"paper":null,"title":"QUACKIE: A NLP Classification Task With Ground Truth Explanations","date":"2020-12-24","arxiv_id":"2012.13190","n_code_links":0,"syntology":null},{"paper":"/paper/sentence-based-model-agnostic-nlp","title":"On the Granularity of Explanations in Model Agnostic NLP Interpretability","date":"2020-12-24","arxiv_id":"2012.13189","n_code_links":1,"syntology":null},{"paper":null,"title":"Are We On The Same Page? Hierarchical Explanation Generation for Planning Tasks in Human-Robot Teaming using Reinforcement Learning","date":"2020-12-22","arxiv_id":"2012.11792","n_code_links":0,"syntology":null},{"paper":null,"title":"Interpreting Deep Learning Models for Epileptic Seizure Detection on EEG signals","date":"2020-12-22","arxiv_id":"2012.11933","n_code_links":0,"syntology":null},{"paper":"/paper/is-the-brain-macroscopically-linear-a-system","title":"Is the brain macroscopically linear? A system identification of resting state dynamics","date":"2020-12-22","arxiv_id":"2012.12351","n_code_links":1,"syntology":null},{"paper":"/paper/recognizing-emotion-cause-in-conversations-1","title":"Recognizing Emotion Cause in Conversations","date":"2020-12-22","arxiv_id":"2012.11820","n_code_links":1,"syntology":null}],"papers_shown":30,"tasks":[{"task":"/task/classification","name":"General Classification","papers":149},{"task":"/task/machine-learning","name":"BIG-bench Machine Learning","papers":119},{"task":"/task/decision-making","name":"Decision Making","papers":84},{"task":"/task/classification-1","name":"Classification","papers":78},{"task":"/task/time-series","name":"Time Series Analysis","papers":66},{"task":"/task/time-series-1","name":"Time Series","papers":57},{"task":"/task/prediction","name":"Prediction","papers":52},{"task":"/task/deep-learning","name":"Deep Learning","papers":51},{"task":"/task/image-classification","name":"Image Classification","papers":50},{"task":"/task/clustering","name":"Clustering","papers":48},{"task":"/task/interpretable-machine-learning","name":"Interpretable Machine Learning","papers":46},{"task":"/task/representation-learning","name":"Representation Learning","papers":43},{"task":"/task/image-classification","name":"image-classification","papers":43},{"task":"/task/feature-selection","name":"feature selection","papers":39},{"task":"/task/regression-1","name":"regression","papers":36},{"task":"/task/question-answering","name":"Question Answering","papers":34},{"task":"/task/reinforcement-learning-1","name":"Reinforcement Learning (RL)","papers":30},{"task":"/task/model","name":"model","papers":29},{"task":"/task/retrieval","name":"Retrieval","papers":28},{"task":"/task/sentence","name":"Sentence","papers":28}],"tasks_shown":20,"n_tasks":572,"usage_by_year":[{"year":"2013","papers":2},{"year":"2014","papers":8},{"year":"2015","papers":22},{"year":"2016","papers":53},{"year":"2017","papers":82},{"year":"2018","papers":191},{"year":"2019","papers":381},{"year":"2020","papers":561},{"year":"2021","papers":22}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/interpretability"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}