{"url":"/task/clustering","name":"Clustering","slug":"clustering","description_markdown":"Clustering is the task of grouping unlabeled data point into disjoint subsets. Each data point is labeled with a single class. The number of classes is not known a priori. The grouping criteria is typically based on the similarity of data points to each other.","categories":[{"name":"Methodology","url":"/area/methodology"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":10718,"papers_with_code":2823,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":5,"subtasks":2,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/timit","name":"TIMIT","full_name":"TIMIT Acoustic-Phonetic Continuous Speech Corpus","num_papers_in_archive":31},{"url":"/dataset/daily-and-sports-activities","name":"Daily and Sports Activities","full_name":"","num_papers_in_archive":1},{"url":"/dataset/furit360","name":"Furit360","full_name":"","num_papers_in_archive":1},{"url":"/dataset/mapreader-data","name":"MapReader Data","full_name":"in GeoHumanities workshop, SIGSPATIAL 2022","num_papers_in_archive":1},{"url":"/dataset/audiosim","name":"VocSim","full_name":"Vocal Similarity Benchmark","num_papers_in_archive":0}],"subtasks":[{"url":"/task/categorical-data-clustering","name":"Categorical data clustering"},{"url":"/task/constrained-clustering","name":"Constrained Clustering"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":2823,"tagged_in_all":10718,"items":[{"url":"/paper/facenet-a-unified-embedding-for-face","title":"FaceNet: A Unified Embedding for Face Recognition and Clustering","date":"2015-03-12","arxiv_id":"1503.03832","repositories_listed":183,"syntology":{"n":154,"n_ran":65,"n_unverified":89,"n_pointer_only":45}},{"url":"/paper/sentence-bert-sentence-embeddings-using","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","date":"2019-08-27","arxiv_id":"1908.10084","repositories_listed":64,"syntology":{"n":58,"n_ran":20,"n_unverified":38,"n_pointer_only":11}},{"url":"/paper/adversarial-autoencoders","title":"Adversarial Autoencoders","date":"2015-11-18","arxiv_id":"1511.05644","repositories_listed":29,"syntology":{"n":12,"n_ran":8,"n_unverified":4,"n_pointer_only":9}},{"url":"/paper/xgboost-a-scalable-tree-boosting-system","title":"XGBoost: A Scalable Tree Boosting System","date":"2016-03-09","arxiv_id":"1603.02754","repositories_listed":28,"syntology":{"n":17,"n_ran":0,"n_unverified":17,"n_pointer_only":0}},{"url":"/paper/solo-segmenting-objects-by-locations","title":"SOLO: Segmenting Objects by Locations","date":"2019-12-10","arxiv_id":"1912.04488","repositories_listed":24,"syntology":null},{"url":"/paper/unsupervised-deep-embedding-for-clustering","title":"Unsupervised Deep Embedding for Clustering Analysis","date":"2015-11-19","arxiv_id":"1511.06335","repositories_listed":23,"syntology":{"n":25,"n_ran":2,"n_unverified":23,"n_pointer_only":3}},{"url":"/paper/deep-speaker-an-end-to-end-neural-speaker","title":"Deep Speaker: an End-to-End Neural Speaker Embedding System","date":"2017-05-05","arxiv_id":"1705.02304","repositories_listed":15,"syntology":{"n":9,"n_ran":7,"n_unverified":2,"n_pointer_only":5}},{"url":"/paper/hubert-self-supervised-speech-representation","title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","date":"2021-06-14","arxiv_id":"2106.07447","repositories_listed":11,"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/variational-deep-embedding-an-unsupervised","title":"Variational Deep Embedding: An Unsupervised and Generative Approach to Clustering","date":"2016-11-16","arxiv_id":"1611.05148","repositories_listed":11,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":2}},{"url":"/paper/towards-k-means-friendly-spaces-simultaneous","title":"Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering","date":"2016-10-15","arxiv_id":"1610.04794","repositories_listed":11,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/key-points-estimation-and-point-instance","title":"Key Points Estimation and Point Instance Segmentation Approach for Lane Detection","date":"2020-02-16","arxiv_id":"2002.06604","repositories_listed":10,"syntology":{"n":8,"n_ran":1,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/catboost-unbiased-boosting-with-categorical","title":"CatBoost: unbiased boosting with categorical features","date":"2017-06-28","arxiv_id":"1706.09516","repositories_listed":10,"syntology":null},{"url":"/paper/deep-clustering-for-unsupervised-learning-of","title":"Deep Clustering for Unsupervised Learning of Visual Features","date":"2018-07-15","arxiv_id":"1807.05520","repositories_listed":9,"syntology":{"n":7,"n_ran":5,"n_unverified":2,"n_pointer_only":4}},{"url":"/paper/leveraging-bert-for-extractive-text","title":"Leveraging BERT for Extractive Text Summarization on Lectures","date":"2019-06-07","arxiv_id":"1906.04165","repositories_listed":8,"syntology":null},{"url":"/paper/entity-embeddings-of-categorical-variables","title":"Entity Embeddings of Categorical Variables","date":"2016-04-22","arxiv_id":"1604.06737","repositories_listed":8,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/deep-clustering-discriminative-embeddings-for","title":"Deep clustering: Discriminative embeddings for segmentation and separation","date":"2015-08-18","arxiv_id":"1508.04306","repositories_listed":8,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":3}},{"url":"/paper/decaf-a-deep-convolutional-activation-feature","title":"DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition","date":"2013-10-06","arxiv_id":"1310.1531","repositories_listed":8,"syntology":{"n":7,"n_ran":1,"n_unverified":6,"n_pointer_only":1}},{"url":"/paper/clustergan-latent-space-clustering-in","title":"ClusterGAN : Latent Space Clustering in Generative Adversarial Networks","date":"2018-09-10","arxiv_id":"1809.03627","repositories_listed":7,"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/a-high-bias-low-variance-introduction-to","title":"A high-bias, low-variance introduction to Machine Learning for physicists","date":"2018-03-23","arxiv_id":"1803.08823","repositories_listed":7,"syntology":{"n":14,"n_ran":2,"n_unverified":12,"n_pointer_only":0}},{"url":"/paper/enhancing-geometric-factors-in-model-learning","title":"Enhancing Geometric Factors in Model Learning and Inference for Object Detection and Instance Segmentation","date":"2020-05-07","arxiv_id":"2005.03572","repositories_listed":6,"syntology":{"n":5,"n_ran":2,"n_unverified":3,"n_pointer_only":5}},{"url":"/paper/agglomerative-fast-super-paramagnetic","title":"Agglomerative Likelihood Clustering","date":"2019-08-02","arxiv_id":"1908.00951","repositories_listed":6,"syntology":null},{"url":"/paper/cluster-gcn-an-efficient-algorithm-for","title":"Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks","date":"2019-05-20","arxiv_id":"1905.07953","repositories_listed":6,"syntology":null},{"url":"/paper/multi-interest-network-with-dynamic-routing","title":"Multi-Interest Network with Dynamic Routing for Recommendation at Tmall","date":"2019-04-17","arxiv_id":"1904.08030","repositories_listed":6,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/invariant-information-distillation-for","title":"Invariant Information Clustering for Unsupervised Image Classification and Segmentation","date":"2018-07-17","arxiv_id":"1807.06653","repositories_listed":6,"syntology":{"n":18,"n_ran":2,"n_unverified":16,"n_pointer_only":0}},{"url":"/paper/som-vae-interpretable-discrete-representation","title":"SOM-VAE: Interpretable Discrete Representation Learning on Time Series","date":"2018-06-06","arxiv_id":"1806.02199","repositories_listed":6,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/graph2vec-learning-distributed","title":"graph2vec: Learning Distributed Representations of Graphs","date":"2017-07-17","arxiv_id":"1707.05005","repositories_listed":6,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/sampling-matters-in-deep-embedding-learning","title":"Sampling Matters in Deep Embedding Learning","date":"2017-06-23","arxiv_id":"1706.07567","repositories_listed":6,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/qcd-aware-recursive-neural-networks-for-jet","title":"QCD-Aware Recursive Neural Networks for Jet Physics","date":"2017-02-02","arxiv_id":"1702.00748","repositories_listed":6,"syntology":{"n":15,"n_ran":0,"n_unverified":15,"n_pointer_only":0}},{"url":"/paper/pypots-a-python-toolbox-for-data-mining-on","title":"PyPOTS: A Python Toolbox for Data Mining on Partially-Observed Time Series","date":"2023-05-30","arxiv_id":"2305.18811","repositories_listed":5,"syntology":{"n":21,"n_ran":0,"n_unverified":21,"n_pointer_only":0}},{"url":"/paper/self-labelling-via-simultaneous-clustering-1","title":"Self-labelling via simultaneous clustering and representation learning","date":"2019-11-13","arxiv_id":"1911.05371","repositories_listed":5,"syntology":{"n":18,"n_ran":7,"n_unverified":11,"n_pointer_only":3}}],"syntology_records":25,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}