{"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/towards-k-means-friendly-spaces-simultaneous","title":"Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering","arxiv_id":"1610.04794","date":"2016-10-15","proceeding":"ICML 2017 8","authors":["Bo Yang","Xiao Fu","Nicholas D. Sidiropoulos","Mingyi Hong"],"abstract":"Most learning approaches treat dimensionality reduction (DR) and clustering\nseparately (i.e., sequentially), but recent research has shown that optimizing\nthe two tasks jointly can substantially improve the performance of both. The\npremise behind the latter genre is that the data samples are obtained via\nlinear transformation of latent representations that are easy to cluster; but\nin practice, the transformation from the latent space to the data can be more\ncomplicated. In this work, we assume that this transformation is an unknown and\npossibly nonlinear function. To recover the `clustering-friendly' latent\nrepresentations and to better cluster the data, we propose a joint DR and\nK-means clustering approach in which DR is accomplished via learning a deep\nneural network (DNN). The motivation is to keep the advantages of jointly\noptimizing the two tasks, while exploiting the deep neural network's ability to\napproximate any nonlinear function. This way, the proposed approach can work\nwell for a broad class of generative models. Towards this end, we carefully\ndesign the DNN structure and the associated joint optimization criterion, and\npropose an effective and scalable algorithm to handle the formulated\noptimization problem. Experiments using different real datasets are employed to\nshowcase the effectiveness of the proposed approach.","url_abs":"http://arxiv.org/abs/1610.04794v2","url_pdf":"http://arxiv.org/pdf/1610.04794v2.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":"towards-k-means-friendly-spaces-simultaneous","repo_url":"https://github.com/boyangumn/DCN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"towards-k-means-friendly-spaces-simultaneous","repo_url":"https://github.com/AaronX121/Deep-Clustering-Network","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"towards-k-means-friendly-spaces-simultaneous","repo_url":"https://github.com/Jagannathrk2020/DCN-New","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"towards-k-means-friendly-spaces-simultaneous","repo_url":"https://github.com/MaziarMF/deep-k-means","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"towards-k-means-friendly-spaces-simultaneous","repo_url":"https://github.com/XiaoxiangLin/DCN-keras","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"towards-k-means-friendly-spaces-simultaneous","repo_url":"https://github.com/astorfi/deep-clustering-kmeans","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"towards-k-means-friendly-spaces-simultaneous","repo_url":"https://github.com/boyangumn/dcn-new","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"towards-k-means-friendly-spaces-simultaneous","repo_url":"https://github.com/linqinghong/Deep-Clustering-Paper","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"towards-k-means-friendly-spaces-simultaneous","repo_url":"https://github.com/probabilistic-and-interactive-ml/breaking-the-reclustering-barrier","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"towards-k-means-friendly-spaces-simultaneous","repo_url":"https://github.com/sarsbug/DCN_keras","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"towards-k-means-friendly-spaces-simultaneous","repo_url":"https://github.com/xuyxu/Deep-Clustering-Network","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"dimensionality-reduction","task_name":"Dimensionality Reduction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1610.04794","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1610.04794"}},"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/boyangumn/DCN","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/XiaoxiangLin/DCN-keras","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/linqinghong/Deep-Clustering-Paper","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/probabilistic-and-interactive-ml/breaking-the-reclustering-barrier","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/astorfi/deep-clustering-kmeans","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sarsbug/DCN_keras","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xuyxu/Deep-Clustering-Network","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/boyangumn/dcn-new","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Jagannathrk2020/DCN-New","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/AaronX121/Deep-Clustering-Network","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MaziarMF/deep-k-means","reach":{"status":"ok","spdx":"GPL-3.0"}}],"summary":{"ran_violates":1,"ran_honours":1,"ran_draft_wrong":1},"by_repo_kind":{"listed":{"samples":3,"ran":3,"repositories":2}},"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":"9a1b2634815f4f53","entry":"acc","repo":"XiaoxiangLin/DCN-keras","repo_kind":"listed","path":"metrics.py","file_url":"https://github.com/XiaoxiangLin/DCN-keras/blob/HEAD/metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9a1b2634815f4f53"}},{"code_sha256_prefix":"756bcc3c5f2e18a4","entry":"evaluate","repo":"astorfi/deep-clustering-kmeans","repo_kind":"listed","path":"mnist.py","file_url":"https://github.com/astorfi/deep-clustering-kmeans/blob/HEAD/mnist.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"756bcc3c5f2e18a4"}},{"code_sha256_prefix":"979bf0d41d1a040c","entry":"solver","repo":"astorfi/deep-clustering-kmeans","repo_kind":"listed","path":"mnist.py","file_url":"https://github.com/astorfi/deep-clustering-kmeans/blob/HEAD/mnist.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"979bf0d41d1a040c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}