{"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/evidential-sparsification-of-multimodal","title":"Evidential Sparsification of Multimodal Latent Spaces in Conditional Variational Autoencoders","arxiv_id":"2010.09164","date":"2020-10-19","proceeding":"NeurIPS 2020 12","authors":["Masha Itkina","Boris Ivanovic","Ransalu Senanayake","Mykel J. Kochenderfer","Marco Pavone"],"abstract":"Discrete latent spaces in variational autoencoders have been shown to effectively capture the data distribution for many real-world problems such as natural language understanding, human intent prediction, and visual scene representation. However, discrete latent spaces need to be sufficiently large to capture the complexities of real-world data, rendering downstream tasks computationally challenging. For instance, performing motion planning in a high-dimensional latent representation of the environment could be intractable. We consider the problem of sparsifying the discrete latent space of a trained conditional variational autoencoder, while preserving its learned multimodality. As a post hoc latent space reduction technique, we use evidential theory to identify the latent classes that receive direct evidence from a particular input condition and filter out those that do not. Experiments on diverse tasks, such as image generation and human behavior prediction, demonstrate the effectiveness of our proposed technique at reducing the discrete latent sample space size of a model while maintaining its learned multimodality.","url_abs":"https://arxiv.org/abs/2010.09164v3","url_pdf":"https://arxiv.org/pdf/2010.09164v3.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":"evidential-sparsification-of-multimodal","repo_url":"https://github.com/sisl/EvidentialSparsification","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"motion-planning","task_name":"Motion Planning"},{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2010.09164","atlas_url":"https://app.syntology.ai/?focus=2010.09164","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.09164"}},"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":"deterministic:regex_extraction","url":"https://github.com/sisl/EvidentialSparsification","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/timbmg/VAE-CVAE-MNIST","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/huyvnphan/PyTorch_CIFAR10","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3,"ran_draft_wrong":1,"ran_fixture":1,"unverified":1},"by_repo_kind":{"official":{"samples":6,"ran":5,"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":6,"samples":[{"code_sha256_prefix":"1a3afafb0116d1f3","entry":"Decoder","repo":"sisl/EvidentialSparsification","repo_kind":"official","path":"FashionMNIST/models.py","file_url":"https://github.com/sisl/EvidentialSparsification/blob/HEAD/FashionMNIST/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1a3afafb0116d1f3"}},{"code_sha256_prefix":"eed44f084396f04f","entry":"Encoder","repo":"sisl/EvidentialSparsification","repo_kind":"official","path":"FashionMNIST/models.py","file_url":"https://github.com/sisl/EvidentialSparsification/blob/HEAD/FashionMNIST/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"eed44f084396f04f"}},{"code_sha256_prefix":"2b4ba414ad352c4d","entry":"Sparsemax","repo":"sisl/EvidentialSparsification","repo_kind":"official","path":"FashionMNIST/models.py","file_url":"https://github.com/sisl/EvidentialSparsification/blob/HEAD/FashionMNIST/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2b4ba414ad352c4d"}},{"code_sha256_prefix":"593b12b533b9922b","entry":"idx2onehot","repo":"sisl/EvidentialSparsification","repo_kind":"official","path":"FashionMNIST/models.py","file_url":"https://github.com/sisl/EvidentialSparsification/blob/HEAD/FashionMNIST/models.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":"593b12b533b9922b"}},{"code_sha256_prefix":"7a7ceb080de51174","entry":"sample_q","repo":"sisl/EvidentialSparsification","repo_kind":"official","path":"FashionMNIST/models.py","file_url":"https://github.com/sisl/EvidentialSparsification/blob/HEAD/FashionMNIST/models.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7a7ceb080de51174"}},{"code_sha256_prefix":"c1882ae03d9d92dc","entry":"VAE","repo":"sisl/EvidentialSparsification","repo_kind":"official","path":"FashionMNIST/models.py","file_url":"https://github.com/sisl/EvidentialSparsification/blob/HEAD/FashionMNIST/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c1882ae03d9d92dc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}