{"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/learning-discrete-and-continuous-factors-of","title":"Learning Discrete and Continuous Factors of Data via Alternating Disentanglement","arxiv_id":"1905.09432","date":"2019-05-23","proceeding":null,"authors":["Yeonwoo Jeong","Hyun Oh Song"],"abstract":"We address the problem of unsupervised disentanglement of discrete and continuous explanatory factors of data. We first show a simple procedure for minimizing the total correlation of the continuous latent variables without having to use a discriminator network or perform importance sampling, via cascading the information flow in the $\\beta$-vae framework. Furthermore, we propose a method which avoids offloading the entire burden of jointly modeling the continuous and discrete factors to the variational encoder by employing a separate discrete inference procedure. This leads to an interesting alternating minimization problem which switches between finding the most likely discrete configuration given the continuous factors and updating the variational encoder based on the computed discrete factors. Experiments show that the proposed method clearly disentangles discrete factors and significantly outperforms current disentanglement methods based on the disentanglement score and inference network classification score. The source code is available at https://github.com/snu-mllab/DisentanglementICML19.","url_abs":"https://arxiv.org/abs/1905.09432v1","url_pdf":"https://arxiv.org/pdf/1905.09432v1.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":"learning-discrete-and-continuous-factors-of","repo_url":"https://github.com/snu-mllab/DisentanglementICML19","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"disentanglement","task_name":"Disentanglement"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1905.09432","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.09432"}},"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/snu-mllab/DisentanglementICML19","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":"e68c6f7c91f3ecc7","entry":"get_shape","repo":"snu-mllab/DisentanglementICML19","repo_kind":"official","path":"tfops/info_op.py","file_url":"https://github.com/snu-mllab/DisentanglementICML19/blob/HEAD/tfops/info_op.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":"e68c6f7c91f3ecc7"}},{"code_sha256_prefix":"9ddb9f3615872422","entry":"piecewise_decay","repo":"snu-mllab/DisentanglementICML19","repo_kind":"official","path":"tfops/lr_op.py","file_url":"https://github.com/snu-mllab/DisentanglementICML19/blob/HEAD/tfops/lr_op.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":"9ddb9f3615872422"}},{"code_sha256_prefix":"089b6e92ad61625f","entry":"sigmoid_cross_entropy","repo":"snu-mllab/DisentanglementICML19","repo_kind":"official","path":"tfops/loss.py","file_url":"https://github.com/snu-mllab/DisentanglementICML19/blob/HEAD/tfops/loss.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":"089b6e92ad61625f"}},{"code_sha256_prefix":"2bc451636d1bb97b","entry":"sigmoid_cross_entropy_without_mean","repo":"snu-mllab/DisentanglementICML19","repo_kind":"official","path":"tfops/loss.py","file_url":"https://github.com/snu-mllab/DisentanglementICML19/blob/HEAD/tfops/loss.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":"2bc451636d1bb97b"}},{"code_sha256_prefix":"eb637c6c7fdcc0d1","entry":"stair_decay","repo":"snu-mllab/DisentanglementICML19","repo_kind":"official","path":"tfops/lr_op.py","file_url":"https://github.com/snu-mllab/DisentanglementICML19/blob/HEAD/tfops/lr_op.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":"eb637c6c7fdcc0d1"}},{"code_sha256_prefix":"9c6cbec3fb802368","entry":"vae_kl_cost","repo":"snu-mllab/DisentanglementICML19","repo_kind":"official","path":"tfops/loss.py","file_url":"https://github.com/snu-mllab/DisentanglementICML19/blob/HEAD/tfops/loss.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":"9c6cbec3fb802368"}},{"code_sha256_prefix":"cf1935d83d4b9568","entry":"vars_info","repo":"snu-mllab/DisentanglementICML19","repo_kind":"official","path":"tfops/info_op.py","file_url":"https://github.com/snu-mllab/DisentanglementICML19/blob/HEAD/tfops/info_op.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":"cf1935d83d4b9568"}},{"code_sha256_prefix":"301713b5d0a31ceb","entry":"vars_info_vl","repo":"snu-mllab/DisentanglementICML19","repo_kind":"official","path":"tfops/info_op.py","file_url":"https://github.com/snu-mllab/DisentanglementICML19/blob/HEAD/tfops/info_op.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":"301713b5d0a31ceb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}