{"url":"/task/active-learning","name":"Active Learning","slug":"active-learning","description_markdown":"**Active Learning** is a paradigm in supervised machine learning which uses fewer training examples to achieve better optimization by iteratively training a predictor, and using the predictor in each iteration to choose the training examples which will increase its chances of finding better configurations and at the same time improving the accuracy of the prediction model\r\n\r\n\r\n<span class=\"description-source\">Source: [Polystore++: Accelerated Polystore System for Heterogeneous Workloads ](https://arxiv.org/abs/1905.10336)</span>","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Methodology","url":"/area/methodology"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":3073,"papers_with_code":913,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"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":16,"subtasks":1,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/active-learning-on-cifar10-10000","slug":"active-learning-on-cifar10-10000","dataset":"CIFAR10 (10,000)","dataset_url":"/dataset/cifar-10","rows_in_archive":7,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"TypiClust","paper_title":"Active Learning on a Budget: Opposite Strategies Suit High and Low Budgets","paper_url":"/paper/active-learning-on-a-budget-opposite","paper_date":"2022-02-06","arxiv_id":"2202.02794","code_links":[{"title":"avihu111/typiclust","url":"https://github.com/avihu111/typiclust"}],"syntology":{"n":5,"n_ran":1,"n_unverified":4,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/cifar-10","name":"CIFAR-10","full_name":"CIFAR-10","num_papers_in_archive":16145},{"url":"/dataset/mnist-8m","name":"MNIST-8M","full_name":"Infinite MNIST","num_papers_in_archive":26},{"url":"/dataset/deepweeds","name":"DeepWeeds","full_name":"","num_papers_in_archive":23},{"url":"/dataset/fdst","name":"FDST","full_name":"Fudan-ShanghaiTech","num_papers_in_archive":18},{"url":"/dataset/dialoglue","name":"DialoGLUE","full_name":"","num_papers_in_archive":17},{"url":"/dataset/groove-midi-dataset","name":"Groove","full_name":"Groove MIDI Dataset","num_papers_in_archive":16},{"url":"/dataset/industrial-benchmark","name":"Industrial Benchmark","full_name":"","num_papers_in_archive":13},{"url":"/dataset/hjdataset","name":"HJDataset","full_name":"","num_papers_in_archive":5},{"url":"/dataset/illness-dataset","name":"Illness-dataset","full_name":"Illness multi-domain textual dataset","num_papers_in_archive":5},{"url":"/dataset/synthia-al","name":"SYNTHIA-AL","full_name":"","num_papers_in_archive":5},{"url":"/dataset/comp6","name":"COMP6","full_name":"COmprehensive Machine-learning Potential","num_papers_in_archive":4},{"url":"/dataset/arxiv-gr-qc","name":"Arxiv GR-QC","full_name":"General Relativity and Quantum Cosmology collaboration network","num_papers_in_archive":3},{"url":"/dataset/goldfinch","name":"Goldfinch","full_name":"GOogLe image-search Dataset","num_papers_in_archive":3},{"url":"/dataset/photoswitch","name":"Photoswitch","full_name":"","num_papers_in_archive":3},{"url":"/dataset/l-bird","name":"L-Bird","full_name":"Large-Bird","num_papers_in_archive":2},{"url":"/dataset/survey-of-active-learning-hyperparameters","name":"Survey of Active Learning Hyperparameters","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/active-object-detection","name":"Active Object Detection"}],"parent_tasks":[{"url":"/task/optical-character-recognition","name":"Optical Character Recognition (OCR)"}],"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":913,"tagged_in_all":3073,"items":[{"url":"/paper/active-learning-for-convolutional-neural","title":"Active Learning for Convolutional Neural Networks: A Core-Set Approach","date":"2017-08-01","arxiv_id":"1708.00489","repositories_listed":11,"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":4}},{"url":"/paper/self-regulated-interactive-sequence-to","title":"Self-Regulated Interactive Sequence-to-Sequence Learning","date":"2019-07-11","arxiv_id":"1907.05190","repositories_listed":7,"syntology":null},{"url":"/paper/190503677","title":"Learning Loss for Active Learning","date":"2019-05-09","arxiv_id":"1905.03677","repositories_listed":7,"syntology":null},{"url":"/paper/deep-batch-active-learning-by-diverse","title":"Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds","date":"2019-06-09","arxiv_id":"1906.03671","repositories_listed":6,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/variational-adversarial-active-learning","title":"Variational Adversarial Active Learning","date":"2019-03-31","arxiv_id":"1904.00370","repositories_listed":6,"syntology":{"n":14,"n_ran":1,"n_unverified":13,"n_pointer_only":0}},{"url":"/paper/few-shot-learning-with-graph-neural-networks","title":"Few-Shot Learning with Graph Neural Networks","date":"2017-11-10","arxiv_id":"1711.04043","repositories_listed":6,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/deep-bayesian-active-learning-with-image-data","title":"Deep Bayesian Active Learning with Image Data","date":"2017-03-08","arxiv_id":"1703.02910","repositories_listed":6,"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/libact-pool-based-active-learning-in-python","title":"libact: Pool-based Active Learning in Python","date":"2017-10-01","arxiv_id":"1710.00379","repositories_listed":5,"syntology":null},{"url":"/paper/active-learning-in-annotating-micro-blogs","title":"Active learning in annotating micro-blogs dealing with e-reputation","date":"2017-06-16","arxiv_id":"1706.05349","repositories_listed":5,"syntology":null},{"url":"/paper/active-learning-by-feature-mixing","title":"Active Learning by Feature Mixing","date":"2022-03-14","arxiv_id":"2203.07034","repositories_listed":4,"syntology":{"n":8,"n_ran":7,"n_unverified":1,"n_pointer_only":2}},{"url":"/paper/causal-bald-deep-bayesian-active-learning-of","title":"Causal-BALD: Deep Bayesian Active Learning of Outcomes to Infer Treatment-Effects from Observational Data","date":"2021-11-03","arxiv_id":"2111.02275","repositories_listed":4,"syntology":{"n":11,"n_ran":7,"n_unverified":4,"n_pointer_only":1}},{"url":"/paper/deterministic-neural-networks-with","title":"Deep Deterministic Uncertainty: A Simple Baseline","date":"2021-02-23","arxiv_id":"2102.11582","repositories_listed":4,"syntology":null},{"url":"/paper/synbols-probing-learning-algorithms-with","title":"Synbols: Probing Learning Algorithms with Synthetic Datasets","date":"2020-09-14","arxiv_id":"2009.06415","repositories_listed":4,"syntology":null},{"url":"/paper/iterative-surrogate-model-optimization-ismo","title":"Iterative Surrogate Model Optimization (ISMO): An active learning algorithm for PDE constrained optimization with deep neural networks","date":"2020-08-13","arxiv_id":"2008.05730","repositories_listed":4,"syntology":null},{"url":"/paper/cost-effective-active-learning-for-deep-image","title":"Cost-Effective Active Learning for Deep Image Classification","date":"2017-01-13","arxiv_id":"1701.03551","repositories_listed":4,"syntology":{"n":13,"n_ran":2,"n_unverified":11,"n_pointer_only":2}},{"url":"/paper/tacogfn-target-conditioned-gflownet-for","title":"TacoGFN: Target-conditioned GFlowNet for Structure-based Drug Design","date":"2023-10-05","arxiv_id":"2310.03223","repositories_listed":3,"syntology":{"n":10,"n_ran":6,"n_unverified":4,"n_pointer_only":1}},{"url":"/paper/let-s-verify-step-by-step-1","title":"Let's Verify Step by Step","date":"2023-05-31","arxiv_id":"2305.20050","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/creating-custom-event-data-without","title":"Creating Custom Event Data Without Dictionaries: A Bag-of-Tricks","date":"2023-04-03","arxiv_id":"2304.01331","repositories_listed":3,"syntology":null},{"url":"/paper/black-box-batch-active-learning-for","title":"Black-Box Batch Active Learning for Regression","date":"2023-02-17","arxiv_id":"2302.08981","repositories_listed":3,"syntology":{"n":13,"n_ran":8,"n_unverified":5,"n_pointer_only":8}},{"url":"/paper/sample-efficient-multi-objective-learning-via","title":"Sample-Efficient Multi-Objective Learning via Generalized Policy Improvement Prioritization","date":"2023-01-18","arxiv_id":"2301.07784","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/simple-techniques-work-surprisingly-well-for","title":"Simple Techniques Work Surprisingly Well for Neural Network Test Prioritization and Active Learning (Replicability Study)","date":"2022-05-02","arxiv_id":"2205.00664","repositories_listed":3,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/active-learning-with-maskal-reduces","title":"Active learning with MaskAL reduces annotation effort for training Mask R-CNN","date":"2021-12-13","arxiv_id":"2112.06586","repositories_listed":3,"syntology":null},{"url":"/paper/egl-extending-expected-gradient-length-to","title":"Bayesian Uncertainty and Expected Gradient Length -- Regression: Two Sides Of The Same Coin?","date":"2021-04-19","arxiv_id":"2104.09493","repositories_listed":3,"syntology":null},{"url":"/paper/can-active-learning-preemptively-mitigate","title":"Can Active Learning Preemptively Mitigate Fairness Issues?","date":"2021-04-14","arxiv_id":"2104.06879","repositories_listed":3,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/fast-bayesian-force-fields-from-active","title":"Bayesian Force Fields from Active Learning for Simulation of Inter-Dimensional Transformation of Stanene","date":"2020-08-26","arxiv_id":"2008.11796","repositories_listed":3,"syntology":null},{"url":"/paper/deep-active-learning-for-axon-myelin","title":"Deep Active Learning for Axon-Myelin Segmentation on Histology Data","date":"2019-07-11","arxiv_id":"1907.05143","repositories_listed":3,"syntology":null},{"url":"/paper/batchbald-efficient-and-diverse-batch","title":"BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning","date":"2019-06-19","arxiv_id":"1906.08158","repositories_listed":3,"syntology":{"n":8,"n_ran":1,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/alipy-active-learning-in-python","title":"ALiPy: Active Learning in Python","date":"2019-01-12","arxiv_id":"1901.03802","repositories_listed":3,"syntology":null},{"url":"/paper/an-overview-and-a-benchmark-of-active","title":"An Overview and a Benchmark of Active Learning for Outlier Detection with One-Class Classifiers","date":"2018-08-14","arxiv_id":"1808.04759","repositories_listed":3,"syntology":null},{"url":"/paper/less-is-more-sampling-chemical-space-with","title":"Less is more: sampling chemical space with active learning","date":"2018-01-28","arxiv_id":"1801.09319","repositories_listed":3,"syntology":null}],"syntology_records":15,"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"}}