{"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/simple-scalable-and-stable-variational-deep","title":"Simple, Scalable, and Stable Variational Deep Clustering","arxiv_id":"2005.08047","date":"2020-05-16","proceeding":null,"authors":["Lele Cao","Sahar Asadi","Wenfei Zhu","Christian Schmidli","Michael Sjöberg"],"abstract":"Deep clustering (DC) has become the state-of-the-art for unsupervised clustering. In principle, DC represents a variety of unsupervised methods that jointly learn the underlying clusters and the latent representation directly from unstructured datasets. However, DC methods are generally poorly applied due to high operational costs, low scalability, and unstable results. In this paper, we first evaluate several popular DC variants in the context of industrial applicability using eight empirical criteria. We then choose to focus on variational deep clustering (VDC) methods, since they mostly meet those criteria except for simplicity, scalability, and stability. To address these three unmet criteria, we introduce four generic algorithmic improvements: initial $\\gamma$-training, periodic $\\beta$-annealing, mini-batch GMM (Gaussian mixture model) initialization, and inverse min-max transform. We also propose a novel clustering algorithm S3VDC (simple, scalable, and stable VDC) that incorporates all those improvements. Our experiments show that S3VDC outperforms the state-of-the-art on both benchmark tasks and a large unstructured industrial dataset without any ground truth label. In addition, we analytically evaluate the usability and interpretability of S3VDC.","url_abs":"https://arxiv.org/abs/2005.08047v2","url_pdf":"https://arxiv.org/pdf/2005.08047v2.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":"simple-scalable-and-stable-variational-deep","repo_url":"https://github.com/king/s3vdc","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"simple-scalable-and-stable-variational-deep","repo_url":"https://github.com/caolele/caolele.github.io","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"deep-clustering","task_name":"Deep Clustering"}],"methods":[{"method_slug":"interpretability","method_name":"Interpretability"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2005.08047","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.08047"}},"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/king/s3vdc","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/caolele/caolele.github.io","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"ran":0,"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":"29cf17f228d80bc1","entry":"check_array_feature","repo":"king/s3vdc","repo_kind":"official","path":"lib/check_array_feature.py","file_url":"https://github.com/king/s3vdc/blob/HEAD/lib/check_array_feature.py","link_basis":"first_harvest_node","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":"29cf17f228d80bc1"}},{"code_sha256_prefix":"6fe92c82e05db3ef","entry":"find_feature_column","repo":"king/s3vdc","repo_kind":"official","path":"lib/find_feature_column.py","file_url":"https://github.com/king/s3vdc/blob/HEAD/lib/find_feature_column.py","link_basis":"first_harvest_node","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":"6fe92c82e05db3ef"}},{"code_sha256_prefix":"3e79e980eccc4c39","entry":"metric_calinski_harabaz","repo":"king/s3vdc","repo_kind":"official","path":"lib/calinski_harabaz.py","file_url":"https://github.com/king/s3vdc/blob/HEAD/lib/calinski_harabaz.py","link_basis":"first_harvest_node","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":"3e79e980eccc4c39"}},{"code_sha256_prefix":"29fa774c37796626","entry":"metric_cluster_separation","repo":"king/s3vdc","repo_kind":"official","path":"lib/cluster_separation.py","file_url":"https://github.com/king/s3vdc/blob/HEAD/lib/cluster_separation.py","link_basis":"first_harvest_node","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":"29fa774c37796626"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}