{"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/relevance-factor-vae-learning-and-identifying","title":"Relevance Factor VAE: Learning and Identifying Disentangled Factors","arxiv_id":"1902.01568","date":"2019-02-05","proceeding":null,"authors":["Minyoung Kim","Yuting Wang","Pritish Sahu","Vladimir Pavlovic"],"abstract":"We propose a novel VAE-based deep auto-encoder model that can learn\ndisentangled latent representations in a fully unsupervised manner, endowed\nwith the ability to identify all meaningful sources of variation and their\ncardinality. Our model, dubbed Relevance-Factor-VAE, leverages the total\ncorrelation (TC) in the latent space to achieve the disentanglement goal, but\nalso addresses the key issue of existing approaches which cannot distinguish\nbetween meaningful and nuisance factors of latent variation, often the source\nof considerable degradation in disentanglement performance. We tackle this\nissue by introducing the so-called relevance indicator variables that can be\nautomatically learned from data, together with the VAE parameters. Our model\neffectively focuses the TC loss onto the relevant factors only by tolerating\nlarge prior KL divergences, a desideratum justified by our semi-parametric\ntheoretical analysis. Using a suite of disentanglement metrics, including a\nnewly proposed one, as well as qualitative evidence, we demonstrate that our\nmodel outperforms existing methods across several challenging benchmark\ndatasets.","url_abs":"http://arxiv.org/abs/1902.01568v1","url_pdf":"http://arxiv.org/pdf/1902.01568v1.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":"relevance-factor-vae-learning-and-identifying","repo_url":"https://github.com/ThomasMrY/RF-VAE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","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=1902.01568","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.01568"}},"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/ThomasMrY/RF-VAE","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"ran_violates":1,"unverified":4},"by_repo_kind":{"listed":{"samples":6,"ran":2,"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":"6523d8d6272a3cc5","entry":"is_power_of_2","repo":"ThomasMrY/RF-VAE","repo_kind":"listed","path":"dataset.py","file_url":"https://github.com/ThomasMrY/RF-VAE/blob/HEAD/dataset.py","link_basis":"harvester_set","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":"6523d8d6272a3cc5"}},{"code_sha256_prefix":"f017532fc389cbfe","entry":"str2bool","repo":"ThomasMrY/RF-VAE","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/ThomasMrY/RF-VAE/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f017532fc389cbfe"}},{"code_sha256_prefix":"b83a9785aff580b5","entry":"entropy","repo":"ThomasMrY/RF-VAE","repo_kind":"listed","path":"ops.py","file_url":"https://github.com/ThomasMrY/RF-VAE/blob/HEAD/ops.py","link_basis":"harvester_set","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":"b83a9785aff580b5"}},{"code_sha256_prefix":"915d409704261ce3","entry":"kl_divergence","repo":"ThomasMrY/RF-VAE","repo_kind":"listed","path":"ops.py","file_url":"https://github.com/ThomasMrY/RF-VAE/blob/HEAD/ops.py","link_basis":"harvester_set","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":"915d409704261ce3"}},{"code_sha256_prefix":"2cbe0cbb9e1cf86e","entry":"recon_loss","repo":"ThomasMrY/RF-VAE","repo_kind":"listed","path":"ops.py","file_url":"https://github.com/ThomasMrY/RF-VAE/blob/HEAD/ops.py","link_basis":"harvester_set","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":"2cbe0cbb9e1cf86e"}},{"code_sha256_prefix":"f48944b54ecf0097","entry":"return_data","repo":"ThomasMrY/RF-VAE","repo_kind":"listed","path":"dataset.py","file_url":"https://github.com/ThomasMrY/RF-VAE/blob/HEAD/dataset.py","link_basis":"harvester_set","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":"f48944b54ecf0097"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}