{"url":"/task/automl","name":"AutoML","slug":"automl","description_markdown":"Automated Machine Learning (**AutoML**) is a general concept which covers diverse techniques for automated model learning including automatic data preprocessing, architecture search, and model selection.\nSource: Evaluating recommender systems for AI-driven data science (1905.09205)\n\n\n<span class=\"description-source\">Source: [CHOPT : Automated Hyperparameter Optimization Framework for Cloud-Based Machine Learning Platforms ](https://arxiv.org/abs/1810.03527)</span>","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":641,"papers_with_code":295,"benchmarks":4,"benchmark_tables_in_archive":4,"benchmark_tables_shown":4,"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":9,"subtasks":3,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/automl-on-madeline","slug":"automl-on-madeline","dataset":"Chalearn-AutoML-1","dataset_url":"/dataset/madeline","rows_in_archive":8,"metrics":["Rank (AutoML5)","Set1 (F1)","Set2 (PAC)","Set3 (AUC)","Set4 (ABS)","Set5 (BAC)","Duration"],"first_row_in_archive_order":{"model":"aad_freiburg","paper_title":"Analysis of the AutoML Challenge Series 2015–2018","paper_url":"/paper/analysis-of-the-automl-challenge-series-2015","paper_date":"2019-05-18","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/automl-on-breast-cancer-coimbra-data-set","slug":"automl-on-breast-cancer-coimbra-data-set","dataset":"Breast Cancer Coimbra Data Set","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Logistic Regression","paper_title":"OptiMindTune: A Multi-Agent Framework for Intelligent Hyperparameter Optimization","paper_url":"/paper/optimindtune-a-multi-agent-framework-for","paper_date":"2025-05-25","arxiv_id":"2505.19205","code_links":[{"title":"MeherBhaskar/OptiMindTune","url":"https://github.com/MeherBhaskar/OptiMindTune"}],"syntology":null}},{"leaderboard":"/sota/automl-on-ordinaldataset","slug":"automl-on-ordinaldataset","dataset":"OrdinalDataset","dataset_url":"/dataset/ordinaldataset","rows_in_archive":1,"metrics":["1:1 Accuracy"],"first_row_in_archive_order":{"model":"Zero-shot-BERT-SORT","paper_title":"BERT-Sort: A Zero-shot MLM Semantic Encoder on Ordinal Features for AutoML","paper_url":"/paper/bert-sort-a-zero-shot-mlm-semantic-encoder-on","paper_date":"2022-06-01","arxiv_id":null,"code_links":[{"title":"marscod/BERT-Sort","url":"https://github.com/marscod/BERT-Sort"}],"syntology":null}},{"leaderboard":"/sota/automl-on-wine","slug":"automl-on-wine","dataset":"Wine","dataset_url":"/dataset/wine","rows_in_archive":1,"metrics":["accuracy"],"first_row_in_archive_order":{"model":"Logistic Regression","paper_title":"OptiMindTune: A Multi-Agent Framework for Intelligent Hyperparameter Optimization","paper_url":"/paper/optimindtune-a-multi-agent-framework-for","paper_date":"2025-05-25","arxiv_id":"2505.19205","code_links":[{"title":"MeherBhaskar/OptiMindTune","url":"https://github.com/MeherBhaskar/OptiMindTune"}],"syntology":null}}],"datasets":[{"url":"/dataset/nas-bench-101","name":"NAS-Bench-101","full_name":"","num_papers_in_archive":152},{"url":"/dataset/medmnist","name":"MedMNIST","full_name":"","num_papers_in_archive":59},{"url":"/dataset/pmlb","name":"PMLB","full_name":"Penn Machine Learning Benchmarks","num_papers_in_archive":42},{"url":"/dataset/nas-bench-1shot1","name":"NAS-Bench-1Shot1","full_name":"","num_papers_in_archive":24},{"url":"/dataset/css10","name":"CSS10","full_name":"","num_papers_in_archive":22},{"url":"/dataset/wine","name":"Wine","full_name":"Wine Data Set","num_papers_in_archive":11},{"url":"/dataset/madeline","name":"Chalearn-AutoML-1","full_name":"Chalearn-AutoML-1","num_papers_in_archive":1},{"url":"/dataset/genotex","name":"GenoTEX","full_name":"An LLM Agent Benchmark for Automated Gene Expression Data Analysis","num_papers_in_archive":1},{"url":"/dataset/ordinaldataset","name":"OrdinalDataset","full_name":"Ordinal Encoding Data set","num_papers_in_archive":1}],"subtasks":[{"url":"/task/architecture-search","name":"Neural Architecture Search"},{"url":"/task/automated-feature-engineering","name":"Automated Feature Engineering"},{"url":"/task/hyperparameter-optimization","name":"Hyperparameter Optimization"}],"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":295,"tagged_in_all":641,"items":[{"url":"/paper/efficientdet-scalable-and-efficient-object","title":"EfficientDet: Scalable and Efficient Object Detection","date":"2019-11-20","arxiv_id":"1911.09070","repositories_listed":64,"syntology":{"n":70,"n_ran":11,"n_unverified":59,"n_pointer_only":3}},{"url":"/paper/efficientnetv2-smaller-models-and-faster","title":"EfficientNetV2: Smaller Models and Faster Training","date":"2021-04-01","arxiv_id":"2104.00298","repositories_listed":26,"syntology":{"n":79,"n_ran":41,"n_unverified":38,"n_pointer_only":10}},{"url":"/paper/mixnet-mixed-depthwise-convolutional-kernels","title":"MixConv: Mixed Depthwise Convolutional Kernels","date":"2019-07-22","arxiv_id":"1907.09595","repositories_listed":13,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/auto-keras-efficient-neural-architecture","title":"Auto-Keras: An Efficient Neural Architecture Search System","date":"2018-06-27","arxiv_id":"1806.10282","repositories_listed":13,"syntology":{"n":6,"n_ran":3,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/amc-automl-for-model-compression-and","title":"AMC: AutoML for Model Compression and Acceleration on Mobile Devices","date":"2018-02-10","arxiv_id":"1802.03494","repositories_listed":12,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/once-for-all-train-one-network-and-specialize","title":"Once-for-All: Train One Network and Specialize it for Efficient Deployment","date":"2019-08-26","arxiv_id":"1908.09791","repositories_listed":10,"syntology":{"n":34,"n_ran":4,"n_unverified":30,"n_pointer_only":0}},{"url":"/paper/the-machine-learning-bazaar-harnessing-the-ml","title":"The Machine Learning Bazaar: Harnessing the ML Ecosystem for Effective System Development","date":"2019-05-22","arxiv_id":"1905.08942","repositories_listed":8,"syntology":null},{"url":"/paper/meta-learning-a-real-time-tabular-automl","title":"TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second","date":"2022-07-05","arxiv_id":"2207.01848","repositories_listed":7,"syntology":{"n":4,"n_ran":1,"n_unverified":3,"n_pointer_only":1}},{"url":"/paper/autogluon-tabular-robust-and-accurate-automl","title":"AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data","date":"2020-03-13","arxiv_id":"2003.06505","repositories_listed":7,"syntology":{"n":11,"n_ran":0,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/retrieve-merge-predict-augmenting-tables-with","title":"Retrieve, Merge, Predict: Augmenting Tables with Data Lakes","date":"2024-02-09","arxiv_id":"2402.06282","repositories_listed":5,"syntology":null},{"url":"/paper/mfes-hb-efficient-hyperband-with-multi","title":"MFES-HB: Efficient Hyperband with Multi-Fidelity Quality Measurements","date":"2020-12-05","arxiv_id":"2012.03011","repositories_listed":5,"syntology":null},{"url":"/paper/auto-sklearn-2-0-the-next-generation","title":"Auto-Sklearn 2.0: Hands-free AutoML via Meta-Learning","date":"2020-07-08","arxiv_id":"2007.04074","repositories_listed":4,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/safe-ml-surrogate-assisted-feature-extraction","title":"SAFE ML: Surrogate Assisted Feature Extraction for Model Learning","date":"2019-02-28","arxiv_id":"1902.11035","repositories_listed":4,"syntology":null},{"url":"/paper/benchmarking-automatic-machine-learning","title":"Benchmarking Automatic Machine Learning Frameworks","date":"2018-08-17","arxiv_id":"1808.06492","repositories_listed":4,"syntology":null},{"url":"/paper/lemur-neural-network-dataset-towards-seamless","title":"LEMUR Neural Network Dataset: Towards Seamless AutoML","date":"2025-04-14","arxiv_id":"2504.10552","repositories_listed":3,"syntology":null},{"url":"/paper/tabrepo-a-large-scale-repository-of-tabular","title":"TabRepo: A Large Scale Repository of Tabular Model Evaluations and its AutoML Applications","date":"2023-11-06","arxiv_id":"2311.02971","repositories_listed":3,"syntology":{"n":8,"n_ran":8,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/autogluon-timeseries-automl-for-probabilistic","title":"AutoGluon-TimeSeries: AutoML for Probabilistic Time Series Forecasting","date":"2023-08-10","arxiv_id":"2308.05566","repositories_listed":3,"syntology":null},{"url":"/paper/automl-two-sample-test","title":"AutoML Two-Sample Test","date":"2022-06-17","arxiv_id":"2206.08843","repositories_listed":3,"syntology":{"n":11,"n_ran":10,"n_unverified":1,"n_pointer_only":2}},{"url":"/paper/medmnist-v2-a-large-scale-lightweight","title":"MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classification","date":"2021-10-27","arxiv_id":"2110.14795","repositories_listed":3,"syntology":null},{"url":"/paper/lightautoml-automl-solution-for-a-large","title":"LightAutoML: AutoML Solution for a Large Financial Services Ecosystem","date":"2021-09-03","arxiv_id":"2109.01528","repositories_listed":3,"syntology":null},{"url":"/paper/volcanoml-speeding-up-end-to-end-automl-via","title":"VolcanoML: Speeding up End-to-End AutoML via Scalable Search Space Decomposition","date":"2021-07-19","arxiv_id":"2107.08861","repositories_listed":3,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/autosf-towards-automatic-scoring-function","title":"Bilinear Scoring Function Search for Knowledge Graph Learning","date":"2021-07-01","arxiv_id":"2107.00184","repositories_listed":3,"syntology":null},{"url":"/paper/efficient-relation-aware-scoring-function","title":"Efficient Relation-aware Scoring Function Search for Knowledge Graph Embedding","date":"2021-04-22","arxiv_id":"2104.10880","repositories_listed":3,"syntology":null},{"url":"/paper/rethinking-neural-operations-for-diverse","title":"Rethinking Neural Operations for Diverse Tasks","date":"2021-03-29","arxiv_id":"2103.15798","repositories_listed":3,"syntology":{"n":34,"n_ran":18,"n_unverified":16,"n_pointer_only":0}},{"url":"/paper/robust-and-accurate-object-detection-via","title":"Robust and Accurate Object Detection via Adversarial Learning","date":"2021-03-23","arxiv_id":"2103.13886","repositories_listed":3,"syntology":null},{"url":"/paper/medmnist-classification-decathlon-a","title":"MedMNIST Classification Decathlon: A Lightweight AutoML Benchmark for Medical Image Analysis","date":"2020-10-28","arxiv_id":"2010.14925","repositories_listed":3,"syntology":{"n":10,"n_ran":2,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/cardea-an-open-automated-machine-learning","title":"Cardea: An Open Automated Machine Learning Framework for Electronic Health Records","date":"2020-10-01","arxiv_id":"2010.00509","repositories_listed":3,"syntology":null},{"url":"/paper/gama-a-general-automated-machine-learning","title":"GAMA: a General Automated Machine learning Assistant","date":"2020-07-09","arxiv_id":"2007.04911","repositories_listed":3,"syntology":{"n":17,"n_ran":0,"n_unverified":17,"n_pointer_only":0}},{"url":"/paper/autogan-distiller-searching-to-compress","title":"AutoGAN-Distiller: Searching to Compress Generative Adversarial Networks","date":"2020-06-15","arxiv_id":"2006.08198","repositories_listed":3,"syntology":{"n":8,"n_ran":1,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/model-based-asynchronous-hyperparameter","title":"Model-based Asynchronous Hyperparameter and Neural Architecture Search","date":"2020-03-24","arxiv_id":"2003.10865","repositories_listed":3,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}}],"syntology_records":17,"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"}}