{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/improving-k-means-clustering-performance-with","title":"Improving k-Means Clustering Performance with Disentangled Internal Representations","arxiv_id":"2006.04535","date":"2020-06-05","proceeding":null,"authors":["Abien Fred Agarap","Arnulfo P. Azcarraga"],"abstract":"Deep clustering algorithms combine representation learning and clustering by jointly optimizing a clustering loss and a non-clustering loss. In such methods, a deep neural network is used for representation learning together with a clustering network. Instead of following this framework to improve clustering performance, we propose a simpler approach of optimizing the entanglement of the learned latent code representation of an autoencoder. We define entanglement as how close pairs of points from the same class or structure are, relative to pairs of points from different classes or structures. To measure the entanglement of data points, we use the soft nearest neighbor loss, and expand it by introducing an annealing temperature factor. Using our proposed approach, the test clustering accuracy was 96.2% on the MNIST dataset, 85.6% on the Fashion-MNIST dataset, and 79.2% on the EMNIST Balanced dataset, outperforming our baseline models.","url_abs":"https://arxiv.org/abs/2006.04535v1","url_pdf":"https://arxiv.org/pdf/2006.04535v1.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":"improving-k-means-clustering-performance-with","repo_url":"https://gitlab.com/afagarap/pt-snnl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"deep-clustering","task_name":"Deep Clustering"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-clustering","task_name":"Image Clustering"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[{"method_slug":"annealing-snnl","method_name":"Annealing SNNL"}],"datasets_introduced":[],"methods_introduced":[{"slug":"annealing-snnl","name":"Annealing SNNL","full_name":"Soft Nearest Neighbor Loss with Annealing Temperature"}],"results":[{"leaderboard":"/sota/image-classification-on-emnist-balanced","task":"Image Classification","dataset":"EMNIST-Balanced","model":"SNNL-5","rank_in_archive_order":19,"of":20,"metrics":{"Accuracy":"78.5","NMI":"77.6"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-fashion-mnist","task":"Image Classification","dataset":"Fashion-MNIST","model":"SNNL-5","rank_in_archive_order":32,"of":34,"metrics":{"Accuracy":"84.4","NMI":"76.2"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-mnist","task":"Image Classification","dataset":"MNIST","model":"SNNL-5","rank_in_archive_order":79,"of":81,"metrics":{"Accuracy":"95.5"},"uses_additional_data":false},{"leaderboard":"/sota/image-clustering-on-emnist-balanced","task":"Image Clustering","dataset":"EMNIST-Balanced","model":"AE+SNNL","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy":"0.792","NMI":"0.783"},"uses_additional_data":false},{"leaderboard":"/sota/image-clustering-on-emnist-balanced","task":"Image Clustering","dataset":"EMNIST-Balanced","model":"SNNL-8","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"0.35","NMI":"0.442"},"uses_additional_data":false},{"leaderboard":"/sota/image-clustering-on-fashion-mnist","task":"Image Clustering","dataset":"Fashion-MNIST","model":"SNNL-4","rank_in_archive_order":13,"of":13,"metrics":{"Accuracy":"0.555","NMI":"0.574"},"uses_additional_data":false},{"leaderboard":"/sota/image-clustering-on-mnist","task":"Image Clustering","dataset":"MNIST","model":"SNNL-7","rank_in_archive_order":3,"of":3,"metrics":{"NMI":"0.891"},"uses_additional_data":false},{"leaderboard":"/sota/image-clustering-on-mnist-test","task":"Image Clustering","dataset":"MNIST-test","model":"AE+SNNL","rank_in_archive_order":8,"of":11,"metrics":{"Accuracy":"0.962","NMI":"0.903"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2006.04535","atlas_url":"https://app.syntology.ai/?focus=2006.04535","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2006.04535"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2006.04535\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2006.04535"},"call":"get_concepts_for_paper(arxiv_id=\"2006.04535\")"}],"by_repo":[{"repo":"gitlab.com/afagarap/pt-snnl","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"147b9f1d32643c4ca3ecf53597870adf690b1e397f37db4aadc1dd16bffcddae","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}