{"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/2505-10704","title":"ZEUS: Zero-shot Embeddings for Unsupervised Separation of Tabular Data","arxiv_id":"2505.10704","date":"2025-05-15","proceeding":null,"authors":["Patryk Marszałek","Tomasz Kuśmierczyk","Witold Wydmański","Jacek Tabor","Marek Śmieja"],"abstract":"Clustering tabular data remains a significant open challenge in data analysis and machine learning. Unlike for image data, similarity between tabular records often varies across datasets, making the definition of clusters highly dataset-dependent. Furthermore, the absence of supervised signals complicates hyperparameter tuning in deep learning clustering methods, frequently resulting in unstable performance. To address these issues and reduce the need for per-dataset tuning, we adopt an emerging approach in deep learning: zero-shot learning. We propose ZEUS, a self-contained model capable of clustering new datasets without any additional training or fine-tuning. It operates by decomposing complex datasets into meaningful components that can then be clustered effectively. Thanks to pre-training on synthetic datasets generated from a latent-variable prior, it generalizes across various datasets without requiring user intervention. To the best of our knowledge, ZEUS is the first zero-shot method capable of generating embeddings for tabular data in a fully unsupervised manner. Experimental results demonstrate that it performs on par with or better than traditional clustering algorithms and recent deep learning-based methods, while being significantly faster and more user-friendly.","url_abs":"https://arxiv.org/abs/2505.10704v1","url_pdf":"https://arxiv.org/pdf/2505.10704v1.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":"2505-10704","repo_url":"https://github.com/gmum/zeus","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"}],"methods":[{"method_slug":"adopt","method_name":"ADOPT"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2505.10704","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.10704"}},"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":"deterministic:regex_extraction","url":"https://github.com/gmum/zeus","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/vlukiyanov/pt-dec","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/dawnranger/IDEC-pytorch","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/jsvir/idc","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/mdsamad001/G-CEALS-Deep-Clustering-for-Tabular-Data","reach":{"status":"gone","observed_at":"2026-09-16","how":"tree_404+repo_404"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/PriorLabs/tabpfn-extensions","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/clabrugere/pytorch-scarf","reach":null}],"summary":{"ran":5,"unverified":3},"by_repo_kind":{"official":{"samples":3,"ran":1,"repositories":1},"found_in_text":{"samples":5,"ran":4,"repositories":3}},"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":3,"samples":[{"code_sha256_prefix":"e02d2cfb00f60ecd","entry":"ClusterAssignment","repo":"vlukiyanov/pt-dec","repo_kind":"found_in_text","path":"ptdec/dec.py","file_url":"https://github.com/vlukiyanov/pt-dec/blob/HEAD/ptdec/dec.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e02d2cfb00f60ecd"}},{"code_sha256_prefix":"0a5b1f0164507f1a","entry":"DEC","repo":"vlukiyanov/pt-dec","repo_kind":"found_in_text","path":"ptdec/dec.py","file_url":"https://github.com/vlukiyanov/pt-dec/blob/HEAD/ptdec/dec.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0a5b1f0164507f1a"}},{"code_sha256_prefix":"acdb47d8e9641a21","entry":"GatingNet","repo":"jsvir/idc","repo_kind":"found_in_text","path":"model.py","file_url":"https://github.com/jsvir/idc/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"acdb47d8e9641a21"}},{"code_sha256_prefix":"35598d37019944b8","entry":"MLP","repo":"clabrugere/pytorch-scarf","repo_kind":"found_in_text","path":"scarf/model.py","file_url":"https://github.com/clabrugere/pytorch-scarf/blob/HEAD/scarf/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"35598d37019944b8"}},{"code_sha256_prefix":"df4358779e4de127","entry":"TransformerEncoderLayer","repo":"gmum/zeus","repo_kind":"official","path":"zeus/model/zeus.py","file_url":"https://github.com/gmum/zeus/blob/HEAD/zeus/model/zeus.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":"df4358779e4de127"}},{"code_sha256_prefix":"ca5bbfdc9d156c05","entry":"LossType","repo":"gmum/zeus","repo_kind":"official","path":"zeus/model/zeus.py","file_url":"https://github.com/gmum/zeus/blob/HEAD/zeus/model/zeus.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":"ca5bbfdc9d156c05"}},{"code_sha256_prefix":"0827a38960242e75","entry":"SCARF","repo":"clabrugere/pytorch-scarf","repo_kind":"found_in_text","path":"scarf/model.py","file_url":"https://github.com/clabrugere/pytorch-scarf/blob/HEAD/scarf/model.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":"0827a38960242e75"}},{"code_sha256_prefix":"df3cab4a2ac1d917","entry":"ZeusTransformerModel","repo":"gmum/zeus","repo_kind":"official","path":"zeus/model/zeus.py","file_url":"https://github.com/gmum/zeus/blob/HEAD/zeus/model/zeus.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":"df3cab4a2ac1d917"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}