{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/transformation-importance-with-applications","title":"Transformation Importance with Applications to Cosmology","arxiv_id":"2003.01926","date":"2020-03-04","proceeding":null,"authors":["Chandan Singh","Wooseok Ha","Francois Lanusse","Vanessa Boehm","Jia Liu","Bin Yu"],"abstract":"Machine learning lies at the heart of new possibilities for scientific discovery, knowledge generation, and artificial intelligence. Its potential benefits to these fields requires going beyond predictive accuracy and focusing on interpretability. In particular, many scientific problems require interpretations in a domain-specific interpretable feature space (e.g. the frequency domain) whereas attributions to the raw features (e.g. the pixel space) may be unintelligible or even misleading. To address this challenge, we propose TRIM (TRansformation IMportance), a novel approach which attributes importances to features in a transformed space and can be applied post-hoc to a fully trained model. TRIM is motivated by a cosmological parameter estimation problem using deep neural networks (DNNs) on simulated data, but it is generally applicable across domains/models and can be combined with any local interpretation method. In our cosmology example, combining TRIM with contextual decomposition shows promising results for identifying which frequencies a DNN uses, helping cosmologists to understand and validate that the model learns appropriate physical features rather than simulation artifacts.","url_abs":"https://arxiv.org/abs/2003.01926v2","url_pdf":"https://arxiv.org/pdf/2003.01926v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"transformation-importance-with-applications","repo_url":"https://github.com/csinva/transformation-importance","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"transformation-importance-with-applications","repo_url":"https://github.com/csinva/local-vae","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"parameter-estimation","task_name":"parameter estimation"},{"task_slug":"scientific-discovery","task_name":"scientific discovery"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2003.01926","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.01926"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/csinva/transformation-importance","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/csinva/local-vae","reach":null}],"summary":{"ran":1,"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":2,"ran":2,"repositories":1},"listed":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"37a4f94071743f30","entry":"TrimModel","repo":"csinva/local-vae","repo_kind":"listed","path":"lib/trim/trim.py","file_url":"https://github.com/csinva/local-vae/blob/HEAD/lib/trim/trim.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"37a4f94071743f30"}},{"code_sha256_prefix":"b7bb3ddb565dc2ec","entry":"lay_from_w","repo":"csinva/transformation-importance","repo_kind":"official","path":"trim/trim.py","file_url":"https://github.com/csinva/transformation-importance/blob/HEAD/trim/trim.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b7bb3ddb565dc2ec"}},{"code_sha256_prefix":"fbc27409d4e632db","entry":"modularize","repo":"csinva/transformation-importance","repo_kind":"official","path":"trim/trim.py","file_url":"https://github.com/csinva/transformation-importance/blob/HEAD/trim/trim.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fbc27409d4e632db"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}