{"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/addressing-the-topological-defects-of-1","title":"Addressing the Topological Defects of Disentanglement via Distributed Operators","arxiv_id":"2102.05623","date":"2021-02-10","proceeding":null,"authors":["Diane Bouchacourt","Mark Ibrahim","Stéphane Deny"],"abstract":"A core challenge in Machine Learning is to learn to disentangle natural factors of variation in data (e.g. object shape vs. pose). A popular approach to disentanglement consists in learning to map each of these factors to distinct subspaces of a model's latent representation. However, this approach has shown limited empirical success to date. Here, we show that, for a broad family of transformations acting on images--encompassing simple affine transformations such as rotations and translations--this approach to disentanglement introduces topological defects (i.e. discontinuities in the encoder). Motivated by classical results from group representation theory, we study an alternative, more flexible approach to disentanglement which relies on distributed latent operators, potentially acting on the entire latent space. We theoretically and empirically demonstrate the effectiveness of this approach to disentangle affine transformations. Our work lays a theoretical foundation for the recent success of a new generation of models using distributed operators for disentanglement.","url_abs":"https://arxiv.org/abs/2102.05623v1","url_pdf":"https://arxiv.org/pdf/2102.05623v1.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":"addressing-the-topological-defects-of-1","repo_url":"https://github.com/facebookresearch/Addressing-the-Topological-Defects-of-Disentanglement","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"disentanglement","task_name":"Disentanglement"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2102.05623","atlas_url":"https://app.syntology.ai/?focus=2102.05623","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.05623"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/facebookresearch/Addressing-the-Topological-Defects-of-Disentanglement","reach":null}],"summary":{"ran_draft_wrong":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":3,"samples":[{"code_sha256_prefix":"d70c73b5ba311020","entry":"get_directories","repo":"facebookresearch/Addressing-the-Topological-Defects-of-Disentanglement","repo_kind":"official","path":"run_experiments_real.py","file_url":"https://github.com/facebookresearch/Addressing-the-Topological-Defects-of-Disentanglement/blob/HEAD/run_experiments_real.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":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"d70c73b5ba311020"}},{"code_sha256_prefix":"1ba690b99b6b2ad5","entry":"get_param_combinations","repo":"facebookresearch/Addressing-the-Topological-Defects-of-Disentanglement","repo_kind":"official","path":"run_experiments_real.py","file_url":"https://github.com/facebookresearch/Addressing-the-Topological-Defects-of-Disentanglement/blob/HEAD/run_experiments_real.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":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"1ba690b99b6b2ad5"}},{"code_sha256_prefix":"3ff22d69baec8e3d","entry":"get_params","repo":"facebookresearch/Addressing-the-Topological-Defects-of-Disentanglement","repo_kind":"official","path":"run_experiments_real.py","file_url":"https://github.com/facebookresearch/Addressing-the-Topological-Defects-of-Disentanglement/blob/HEAD/run_experiments_real.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":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"3ff22d69baec8e3d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}