{"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/multimodal-generative-models-for-scalable","title":"Multimodal Generative Models for Scalable Weakly-Supervised Learning","arxiv_id":"1802.05335","date":"2018-02-14","proceeding":"NeurIPS 2018 12","authors":["Mike Wu","Noah Goodman"],"abstract":"Multiple modalities often co-occur when describing natural phenomena.\nLearning a joint representation of these modalities should yield deeper and\nmore useful representations. Previous generative approaches to multi-modal\ninput either do not learn a joint distribution or require additional\ncomputation to handle missing data. Here, we introduce a multimodal variational\nautoencoder (MVAE) that uses a product-of-experts inference network and a\nsub-sampled training paradigm to solve the multi-modal inference problem.\nNotably, our model shares parameters to efficiently learn under any combination\nof missing modalities. We apply the MVAE on four datasets and match\nstate-of-the-art performance using many fewer parameters. In addition, we show\nthat the MVAE is directly applicable to weakly-supervised learning, and is\nrobust to incomplete supervision. We then consider two case studies, one of\nlearning image transformations---edge detection, colorization,\nsegmentation---as a set of modalities, followed by one of machine translation\nbetween two languages. We find appealing results across this range of tasks.","url_abs":"http://arxiv.org/abs/1802.05335v3","url_pdf":"http://arxiv.org/pdf/1802.05335v3.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":"multimodal-generative-models-for-scalable","repo_url":"https://github.com/YugeTen/QMVAE-mmdgm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"multimodal-generative-models-for-scalable","repo_url":"https://github.com/gabinsane/multi-vaes-in-robotics","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"CC0-1.0"}},{"paper_slug":"multimodal-generative-models-for-scalable","repo_url":"https://github.com/gabinsane/multimodal-vae-comparison","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multimodal-generative-models-for-scalable","repo_url":"https://github.com/mhw32/multimodal-vae-public","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"colorization","task_name":"Colorization"},{"task_slug":"edge-detection","task_name":"Edge Detection"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"weakly-supervised-learning","task_name":"Weakly-supervised Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1802.05335","atlas_url":"https://app.syntology.ai/?focus=1802.05335","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.05335"}},"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/mhw32/multimodal-vae-public","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gabinsane/multi-vaes-in-robotics","reach":{"status":"ok","spdx":"CC0-1.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/YugeTen/QMVAE-mmdgm","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gabinsane/multimodal-vae-comparison","reach":null}],"summary":{"ran_violates":1},"by_repo_kind":{"listed":{"samples":1,"ran":1,"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":1,"samples":[{"code_sha256_prefix":"069b8e2ab4d7baeb","entry":"manhattan_distance","repo":"gabinsane/multimodal-vae-comparison","repo_kind":"listed","path":"multimodal_compare/eval/eval_cdsprites.py","file_url":"https://github.com/gabinsane/multimodal-vae-comparison/blob/HEAD/multimodal_compare/eval/eval_cdsprites.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"069b8e2ab4d7baeb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}