{"url":"/task/interpretability-techniques-for-deep-learning","name":"Interpretability Techniques for Deep Learning","slug":"interpretability-techniques-for-deep-learning","description_markdown":null,"categories":[{"name":"Miscellaneous","url":"/area/miscellaneous"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":25,"papers_with_code":22,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":2,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/interpretability-techniques-for-deep-learning","slug":"interpretability-techniques-for-deep-learning","dataset":"CausalGym","dataset_url":"/dataset/causalgym","rows_in_archive":7,"metrics":["Log odds-ratio (pythia-6.9b)"],"first_row_in_archive_order":{"model":"DAS","paper_title":"CausalGym: Benchmarking causal interpretability methods on linguistic tasks","paper_url":"/paper/causalgym-benchmarking-causal","paper_date":"2024-02-19","arxiv_id":"2402.12560","code_links":[{"title":"aryamanarora/causalgym","url":"https://github.com/aryamanarora/causalgym"},{"title":"jannik-brinkmann/multilingual-features","url":"https://github.com/jannik-brinkmann/multilingual-features"}],"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}}},{"leaderboard":"/sota/interpretability-techniques-for-deep-learning-1","slug":"interpretability-techniques-for-deep-learning-1","dataset":"CelebA","dataset_url":"/dataset/celeba","rows_in_archive":7,"metrics":["Insertion AUC score"],"first_row_in_archive_order":{"model":"RISE","paper_title":"RISE: Randomized Input Sampling for Explanation of Black-box Models","paper_url":"/paper/rise-randomized-input-sampling-for","paper_date":"2018-06-19","arxiv_id":"1806.07421","code_links":[{"title":"openvinotoolkit/datumaro","url":"https://github.com/openvinotoolkit/datumaro"},{"title":"eclique/RISE","url":"https://github.com/eclique/RISE"},{"title":"dbash/zerowaste","url":"https://github.com/dbash/zerowaste"},{"title":"hysts/pytorch_D-RISE","url":"https://github.com/hysts/pytorch_D-RISE"},{"title":"openvinotoolkit/openvino_xai","url":"https://github.com/openvinotoolkit/openvino_xai"},{"title":"yiskw713/RISE","url":"https://github.com/yiskw713/RISE"},{"title":"wickstrom/relax","url":"https://github.com/wickstrom/relax"},{"title":"tristangomez44/metrics-saliency-maps","url":"https://github.com/tristangomez44/metrics-saliency-maps"},{"title":"vlue-c/Visual-Explanation-Methods-PyTorch","url":"https://github.com/vlue-c/Visual-Explanation-Methods-PyTorch"},{"title":"myurasov/RISE","url":"https://github.com/myurasov/RISE"},{"title":"vlue-c/PyTorch-Explanations","url":"https://github.com/vlue-c/PyTorch-Explanations"},{"title":"palatos/RISE_tf","url":"https://github.com/palatos/RISE_tf"},{"title":"ftorres11/saliencysense","url":"https://github.com/ftorres11/saliencysense"}],"syntology":{"n":34,"n_ran":1,"n_unverified":33,"n_pointer_only":10}}}],"datasets":[{"url":"/dataset/celeba","name":"CelebA","full_name":"CelebFaces Attributes Dataset","num_papers_in_archive":3477},{"url":"/dataset/causalgym","name":"CausalGym","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":22,"of":22,"tagged_in_all":25,"items":[{"url":"/paper/grad-cam-visual-explanations-from-deep","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","date":"2016-10-07","arxiv_id":"1610.02391","repositories_listed":126,"syntology":{"n":141,"n_ran":79,"n_unverified":62,"n_pointer_only":68}},{"url":"/paper/axiomatic-attribution-for-deep-networks","title":"Axiomatic Attribution for Deep Networks","date":"2017-03-04","arxiv_id":"1703.01365","repositories_listed":40,"syntology":{"n":56,"n_ran":36,"n_unverified":20,"n_pointer_only":17}},{"url":"/paper/why-should-i-trust-you-explaining-the","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","date":"2016-02-16","arxiv_id":"1602.04938","repositories_listed":27,"syntology":{"n":19,"n_ran":5,"n_unverified":14,"n_pointer_only":0}},{"url":"/paper/deep-inside-convolutional-networks","title":"Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps","date":"2013-12-20","arxiv_id":"1312.6034","repositories_listed":23,"syntology":{"n":4,"n_ran":1,"n_unverified":3,"n_pointer_only":1}},{"url":"/paper/a-unified-approach-to-interpreting-model","title":"A Unified Approach to Interpreting Model Predictions","date":"2017-05-22","arxiv_id":"1705.07874","repositories_listed":17,"syntology":{"n":8,"n_ran":3,"n_unverified":5,"n_pointer_only":6}},{"url":"/paper/rise-randomized-input-sampling-for","title":"RISE: Randomized Input Sampling for Explanation of Black-box Models","date":"2018-06-19","arxiv_id":"1806.07421","repositories_listed":13,"syntology":{"n":34,"n_ran":1,"n_unverified":33,"n_pointer_only":10}},{"url":"/paper/time-series-saliency-maps-explaining-models","title":"Time series saliency maps: explaining models across multiple domains","date":"2025-05-19","arxiv_id":"2505.13100","repositories_listed":2,"syntology":null},{"url":"/paper/causalgym-benchmarking-causal","title":"CausalGym: Benchmarking causal interpretability methods on linguistic tasks","date":"2024-02-19","arxiv_id":"2402.12560","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/provfl-client-driven-interpretability-of","title":"TraceFL: Interpretability-Driven Debugging in Federated Learning via Neuron Provenance","date":"2023-12-21","arxiv_id":"2312.13632","repositories_listed":2,"syntology":null},{"url":"/paper/exploration-of-interpretability-techniques","title":"Exploration of Interpretability Techniques for Deep COVID-19 Classification using Chest X-ray Images","date":"2020-06-03","arxiv_id":"2006.02570","repositories_listed":2,"syntology":null},{"url":"/paper/selective-brain-damage-measuring-the","title":"What Do Compressed Deep Neural Networks Forget?","date":"2019-11-13","arxiv_id":"1911.05248","repositories_listed":2,"syntology":null},{"url":"/paper/dissecting-and-mitigating-diffusion-bias-via","title":"Dissecting and Mitigating Diffusion Bias via Mechanistic Interpretability","date":"2025-03-26","arxiv_id":"2503.20483","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/ibo-inpainting-based-occlusion-to-enhance","title":"IBO: Inpainting-Based Occlusion to Enhance Explainable Artificial Intelligence Evaluation in Histopathology","date":"2024-08-29","arxiv_id":"2408.16395","repositories_listed":1,"syntology":null},{"url":"/paper/explainable-deep-learning-a-visual-analytics","title":"Explainable Deep Learning: A Visual Analytics Approach with Transition Matrices","date":"2024-03-29","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/less-is-more-fewer-interpretable-region-via","title":"Less is More: Fewer Interpretable Region via Submodular Subset Selection","date":"2024-02-14","arxiv_id":"2402.09164","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/making-sense-of-dependence-efficient-black","title":"Making Sense of Dependence: Efficient Black-box Explanations Using Dependence Measure","date":"2022-06-13","arxiv_id":"2206.06219","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/learning-the-dynamics-of-physical-systems-1","title":"Learning the Dynamics of Physical Systems from Sparse Observations with Finite Element Networks","date":"2022-03-16","arxiv_id":"2203.08852","repositories_listed":1,"syntology":{"n":8,"n_ran":0,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/a-novel-deep-learning-model-for-hotel-demand","title":"A Novel Deep Learning Model for Hotel Demand and Revenue Prediction amid COVID-19","date":"2022-03-08","arxiv_id":"2203.04383","repositories_listed":1,"syntology":null},{"url":"/paper/a-semi-supervised-deep-transfer-learning","title":"A Semi-supervised Deep Transfer Learning Approach for Rolling-Element Bearing Remaining Useful Life Prediction","date":"2021-09-29","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/dissect-disentangled-simultaneous","title":"DISSECT: Disentangled Simultaneous Explanations via Concept Traversals","date":"2021-05-31","arxiv_id":"2105.15164","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/deepnnk-explaining-deep-models-and-their","title":"DeepNNK: Explaining deep models and their generalization using polytope interpolation","date":"2020-07-20","arxiv_id":"2007.10505","repositories_listed":1,"syntology":null},{"url":"/paper/contextual-explanation-networks","title":"Contextual Explanation Networks","date":"2017-05-29","arxiv_id":"1705.10301","repositories_listed":1,"syntology":null}],"syntology_records":12,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}