{"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/generalized-multimodal-elbo-1","title":"Generalized Multimodal ELBO","arxiv_id":"2105.02470","date":"2021-05-06","proceeding":"ICLR 2021 1","authors":["Thomas M. Sutter","Imant Daunhawer","Julia E. Vogt"],"abstract":"Multiple data types naturally co-occur when describing real-world phenomena and learning from them is a long-standing goal in machine learning research. However, existing self-supervised generative models approximating an ELBO are not able to fulfill all desired requirements of multimodal models: their posterior approximation functions lead to a trade-off between the semantic coherence and the ability to learn the joint data distribution. We propose a new, generalized ELBO formulation for multimodal data that overcomes these limitations. The new objective encompasses two previous methods as special cases and combines their benefits without compromises. In extensive experiments, we demonstrate the advantage of the proposed method compared to state-of-the-art models in self-supervised, generative learning tasks.","url_abs":"https://arxiv.org/abs/2105.02470v2","url_pdf":"https://arxiv.org/pdf/2105.02470v2.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":"generalized-multimodal-elbo-1","repo_url":"https://github.com/thomassutter/MoPoE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[{"slug":"polymnist","name":"PolyMNIST","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2105.02470","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.02470"}},"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/thomassutter/MoPoE","reach":null}],"summary":{"ran_draft_wrong":6,"ran_violates":1},"by_repo_kind":{"official":{"samples":7,"ran":7,"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":7,"samples":[{"code_sha256_prefix":"592bc368676c0eaa","entry":"calc_alphaJSD_modalities_mixture","repo":"thomassutter/MoPoE","repo_kind":"official","path":"divergence_measures/mm_div.py","file_url":"https://github.com/thomassutter/MoPoE/blob/HEAD/divergence_measures/mm_div.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"592bc368676c0eaa"}},{"code_sha256_prefix":"28c672fac93e4998","entry":"calc_entropy_gauss","repo":"thomassutter/MoPoE","repo_kind":"official","path":"divergence_measures/mm_div.py","file_url":"https://github.com/thomassutter/MoPoE/blob/HEAD/divergence_measures/mm_div.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"28c672fac93e4998"}},{"code_sha256_prefix":"2d7b4752b94220b4","entry":"calc_gaussian_scaling_factor","repo":"thomassutter/MoPoE","repo_kind":"official","path":"divergence_measures/mm_div.py","file_url":"https://github.com/thomassutter/MoPoE/blob/HEAD/divergence_measures/mm_div.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2d7b4752b94220b4"}},{"code_sha256_prefix":"f69b626c6821c142","entry":"calc_gaussian_scaling_factor_self","repo":"thomassutter/MoPoE","repo_kind":"official","path":"divergence_measures/mm_div.py","file_url":"https://github.com/thomassutter/MoPoE/blob/HEAD/divergence_measures/mm_div.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f69b626c6821c142"}},{"code_sha256_prefix":"41b518dd975e83e1","entry":"calc_kl_divergence_lb_gauss_mixture","repo":"thomassutter/MoPoE","repo_kind":"official","path":"divergence_measures/mm_div.py","file_url":"https://github.com/thomassutter/MoPoE/blob/HEAD/divergence_measures/mm_div.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"41b518dd975e83e1"}},{"code_sha256_prefix":"a365b2e3a88fee0e","entry":"calc_kl_divergence_ub_gauss_mixture","repo":"thomassutter/MoPoE","repo_kind":"official","path":"divergence_measures/mm_div.py","file_url":"https://github.com/thomassutter/MoPoE/blob/HEAD/divergence_measures/mm_div.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a365b2e3a88fee0e"}},{"code_sha256_prefix":"8506d82fb72d0fb7","entry":"reweight_weights","repo":"thomassutter/MoPoE","repo_kind":"official","path":"divergence_measures/mm_div.py","file_url":"https://github.com/thomassutter/MoPoE/blob/HEAD/divergence_measures/mm_div.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8506d82fb72d0fb7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}