{"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/data-overlap-a-prerequisite-for","title":"Overlooked Implications of the Reconstruction Loss for VAE Disentanglement","arxiv_id":"2202.13341","date":"2022-02-27","proceeding":null,"authors":["Nathan Michlo","Richard Klein","Steven James"],"abstract":"Learning disentangled representations with variational autoencoders (VAEs) is often attributed to the regularisation component of the loss. In this work, we highlight the interaction between data and the reconstruction term of the loss as the main contributor to disentanglement in VAEs. We show that standard benchmark datasets have unintended correlations between their subjective ground-truth factors and perceived axes in the data according to typical VAE reconstruction losses. Our work exploits this relationship to provide a theory for what constitutes an adversarial dataset under a given reconstruction loss. We verify this by constructing an example dataset that prevents disentanglement in state-of-the-art frameworks while maintaining human-intuitive ground-truth factors. Finally, we re-enable disentanglement by designing an example reconstruction loss that is once again able to perceive the ground-truth factors. Our findings demonstrate the subjective nature of disentanglement and the importance of considering the interaction between the ground-truth factors, data and notably, the reconstruction loss, which is under-recognised in the literature.","url_abs":"https://arxiv.org/abs/2202.13341v3","url_pdf":"https://arxiv.org/pdf/2202.13341v3.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":"data-overlap-a-prerequisite-for","repo_url":"https://github.com/nmichlo/disent","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"disentanglement","task_name":"Disentanglement"}],"methods":[],"datasets_introduced":[{"slug":"xysquares","name":"XYSquares","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2202.13341","atlas_url":"https://app.syntology.ai/?focus=2202.13341","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.13341"}},"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/nmichlo/disent","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"unverified":1},"by_repo_kind":{"official":{"samples":3,"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":"a7e61db586268ded","entry":"compute_axis_score","repo":"nmichlo/disent","repo_kind":"official","path":"disent/metrics/_factored_components.py","file_url":"https://github.com/nmichlo/disent/blob/HEAD/disent/metrics/_factored_components.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a7e61db586268ded"}},{"code_sha256_prefix":"353304daf1a3fbec","entry":"compute_flatness","repo":"nmichlo/disent","repo_kind":"official","path":"disent/metrics/_flatness.py","file_url":"https://github.com/nmichlo/disent/blob/HEAD/disent/metrics/_flatness.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"353304daf1a3fbec"}},{"code_sha256_prefix":"4ae1225700e757f0","entry":"filter_inactive_factors","repo":"nmichlo/disent","repo_kind":"official","path":"disent/metrics/_flatness.py","file_url":"https://github.com/nmichlo/disent/blob/HEAD/disent/metrics/_flatness.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":"4ae1225700e757f0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}