{"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/categorical-normalizing-flows-via-continuous","title":"Categorical Normalizing Flows via Continuous Transformations","arxiv_id":"2006.09790","date":"2020-06-17","proceeding":"ICLR 2021 1","authors":["Phillip Lippe","Efstratios Gavves"],"abstract":"Despite their popularity, to date, the application of normalizing flows on categorical data stays limited. The current practice of using dequantization to map discrete data to a continuous space is inapplicable as categorical data has no intrinsic order. Instead, categorical data have complex and latent relations that must be inferred, like the synonymy between words. In this paper, we investigate \\emph{Categorical Normalizing Flows}, that is normalizing flows for categorical data. By casting the encoding of categorical data in continuous space as a variational inference problem, we jointly optimize the continuous representation and the model likelihood. Using a factorized decoder, we introduce an inductive bias to model any interactions in the normalizing flow. As a consequence, we do not only simplify the optimization compared to having a joint decoder, but also make it possible to scale up to a large number of categories that is currently impossible with discrete normalizing flows. Based on Categorical Normalizing Flows, we propose GraphCNF a permutation-invariant generative model on graphs. GraphCNF implements a three step approach modeling the nodes, edges and adjacency matrix stepwise to increase efficiency. On molecule generation, GraphCNF outperforms both one-shot and autoregressive flow-based state-of-the-art.","url_abs":"https://arxiv.org/abs/2006.09790v3","url_pdf":"https://arxiv.org/pdf/2006.09790v3.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":"categorical-normalizing-flows-via-continuous","repo_url":"https://github.com/phlippe/CategoricalNF","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"inductive-bias","task_name":"Inductive Bias"},{"task_slug":"variational-inference","task_name":"Variational Inference"}],"methods":[{"method_slug":"normalizing-flows","method_name":"Normalizing Flows"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2006.09790","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.09790"}},"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/phlippe/CategoricalNF","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":8},"by_repo_kind":{"official":{"samples":8,"ran":0,"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":"24db3da051806583","entry":"add_scheduler_parameters","repo":"phlippe/CategoricalNF","repo_kind":"official","path":"general/parameter_scheduler.py","file_url":"https://github.com/phlippe/CategoricalNF/blob/HEAD/general/parameter_scheduler.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"24db3da051806583"}},{"code_sha256_prefix":"b8b3ef597042e614","entry":"create_embed_layer","repo":"phlippe/CategoricalNF","repo_kind":"official","path":"layers/categorical_encoding/decoder.py","file_url":"https://github.com/phlippe/CategoricalNF/blob/HEAD/layers/categorical_encoding/decoder.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b8b3ef597042e614"}},{"code_sha256_prefix":"54d6f181d75d8a50","entry":"load_args","repo":"phlippe/CategoricalNF","repo_kind":"official","path":"general/mutils.py","file_url":"https://github.com/phlippe/CategoricalNF/blob/HEAD/general/mutils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"54d6f181d75d8a50"}},{"code_sha256_prefix":"14bdea82d68b6932","entry":"load_model","repo":"phlippe/CategoricalNF","repo_kind":"official","path":"general/mutils.py","file_url":"https://github.com/phlippe/CategoricalNF/blob/HEAD/general/mutils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"14bdea82d68b6932"}},{"code_sha256_prefix":"42627605b244e295","entry":"load_model_from_args","repo":"phlippe/CategoricalNF","repo_kind":"official","path":"general/mutils.py","file_url":"https://github.com/phlippe/CategoricalNF/blob/HEAD/general/mutils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"42627605b244e295"}},{"code_sha256_prefix":"df4b531564aed649","entry":"logdist","repo":"phlippe/CategoricalNF","repo_kind":"official","path":"images/visu_file.py","file_url":"https://github.com/phlippe/CategoricalNF/blob/HEAD/images/visu_file.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"df4b531564aed649"}},{"code_sha256_prefix":"4f77250b95215cae","entry":"scheduler_args_to_params","repo":"phlippe/CategoricalNF","repo_kind":"official","path":"general/parameter_scheduler.py","file_url":"https://github.com/phlippe/CategoricalNF/blob/HEAD/general/parameter_scheduler.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4f77250b95215cae"}},{"code_sha256_prefix":"2d43a7be1bdc1405","entry":"sort_to_line","repo":"phlippe/CategoricalNF","repo_kind":"official","path":"images/visu_file.py","file_url":"https://github.com/phlippe/CategoricalNF/blob/HEAD/images/visu_file.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2d43a7be1bdc1405"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}