{"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/graphical-normalizing-flows","title":"Graphical Normalizing Flows","arxiv_id":"2006.02548","date":"2020-06-03","proceeding":null,"authors":["Antoine Wehenkel","Gilles Louppe"],"abstract":"Normalizing flows model complex probability distributions by combining a base distribution with a series of bijective neural networks. State-of-the-art architectures rely on coupling and autoregressive transformations to lift up invertible functions from scalars to vectors. In this work, we revisit these transformations as probabilistic graphical models, showing they reduce to Bayesian networks with a pre-defined topology and a learnable density at each node. From this new perspective, we propose the graphical normalizing flow, a new invertible transformation with either a prescribed or a learnable graphical structure. This model provides a promising way to inject domain knowledge into normalizing flows while preserving both the interpretability of Bayesian networks and the representation capacity of normalizing flows. We show that graphical conditioners discover relevant graph structure when we cannot hypothesize it. In addition, we analyze the effect of $\\ell_1$-penalization on the recovered structure and on the quality of the resulting density estimation. Finally, we show that graphical conditioners lead to competitive white box density estimators. Our implementation is available at https://github.com/AWehenkel/DAG-NF.","url_abs":"https://arxiv.org/abs/2006.02548v3","url_pdf":"https://arxiv.org/pdf/2006.02548v3.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":"graphical-normalizing-flows","repo_url":"https://github.com/AWehenkel/DAG-NF","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"graphical-normalizing-flows","repo_url":"https://github.com/AWehenkel/Graphical-Normalizing-Flows","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"graphical-normalizing-flows","repo_url":"https://github.com/metachenyiyan/BreezeForest","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"graphical-normalizing-flows","repo_url":"https://github.com/sobalgi/rhognf","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"density-estimation","task_name":"Density Estimation"}],"methods":[{"method_slug":"interpretability","method_name":"Interpretability"},{"method_slug":"normalizing-flows","method_name":"Normalizing Flows"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2006.02548","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.02548"}},"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/AWehenkel/Graphical-Normalizing-Flows","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sobalgi/rhognf","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/AWehenkel/DAG-NF","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/metachenyiyan/BreezeForest","reach":{"status":"ok"}}],"summary":{"ran_violates":2,"ran_draft_wrong":1},"by_repo_kind":{"listed":{"samples":3,"ran":3,"repositories":2}},"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":3,"samples":[{"code_sha256_prefix":"e75fa796ef0547d0","entry":"add_noise","repo":"AWehenkel/Graphical-Normalizing-Flows","repo_kind":"listed","path":"ImageExperiments.py","file_url":"https://github.com/AWehenkel/Graphical-Normalizing-Flows/blob/HEAD/ImageExperiments.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"e75fa796ef0547d0"}},{"code_sha256_prefix":"8063884138480961","entry":"compute_bpp","repo":"AWehenkel/Graphical-Normalizing-Flows","repo_kind":"listed","path":"ImageExperiments.py","file_url":"https://github.com/AWehenkel/Graphical-Normalizing-Flows/blob/HEAD/ImageExperiments.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"8063884138480961"}},{"code_sha256_prefix":"86ffd11d1a25ab79","entry":"str_to_dot","repo":"sobalgi/rhognf","repo_kind":"listed","path":"ToySimulatedContinuous.py","file_url":"https://github.com/sobalgi/rhognf/blob/HEAD/ToySimulatedContinuous.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"86ffd11d1a25ab79"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}