skactiveml.pool

The skactiveml.pool package implements query strategies for pool-based active learning.

Submodules

skactiveml.pool.multiannotator

skactiveml.pool.utils

Classes

pool.RandomSampling	Random Sampling (RS)
pool.ProbabilisticAL	Multi-class Probabilistic Active Learning (McPAL)
pool.UncertaintySampling	Uncertainty Sampling (US)
pool.EpistemicUncertaintySampling	Epistemic Uncertainty Sampling (EpisUS)
pool.ExpectedErrorReduction	Expected Error Reduction (EER)
pool.MonteCarloEER	Monte Carlo Expected Error Reduction (EER)
pool.ValueOfInformationEER	Value of Information (VOI)
pool.QueryByCommittee	Query-by-Committee (QBC)
pool.Quire	QUerying Informative and Representative Examples (QUIRE)
pool.FourDs	4DS
pool.CostEmbeddingAL	Active Learning with Cost Embedding (ALCE)
pool.ExpectedModelChangeMaximization	Expected Model Change (EMC)
pool.ExpectedModelOutputChange	Regression based Expected Model Output Change (EMOC)
pool.ExpectedModelVarianceReduction	Expected Model Variance Reduction (EMVR)
pool.KLDivergenceMaximization	Regression based Kullback-Leibler Divergence Maximization
pool.GreedySamplingX	Greedy Sampling in the Feature Space (GSx)
pool.GreedySamplingTarget	Greedy Sampling in the Target Space (GSi or GSy)
pool.DiscriminativeAL	Discriminative Active Learning (DAL)
pool.BatchBALD	Batch Bayesian Active Learning by Disagreement (BatchBALD)
pool.Clue	Clustering Uncertainty-weighted Embeddings (CLUE)
pool.DropQuery	Dropout Query (DropQuery)
pool.CoreSet	Core Set
pool.TypiClust	Typical Clustering (TypiClust)
pool.Badge	Batch Active Learning by Diverse Gradient Embedding (BADGE)
pool.ProbCover	Probability Coverage (ProbCover)
pool.ContrastiveAL	Contrastive Active Learning (ContrastiveAL)
pool.GreedyBALD	Greedy Bayesian Active Learning by Disagreement (GreedyBALD)
pool.RegressionTreeBasedAL	Regression Tree-based Active Learning (RT-AL)
pool.SubSamplingWrapper	Sub-sampling Wrapper
pool.ParallelUtilityEstimationWrapper	Parallel Utility Estimation Wrapper
pool.Falcun	Fast Active Learning by Contrastive UNcertainty (FALCUN)
pool.MaxHerding	This class implements the MaxHerding query strategy [R362e6a09cf34-1], which greedily selects batch_size unlabeled samples that most increase a smooth, kernel-based coverage objective in embedding space, accounting for the already labeled set.

Functions

pool.cost_reduction	Calculate the expected cost reduction.
pool.uncertainty_scores	Computes uncertainty scores.
pool.expected_average_precision	Calculate the expected average precision [R24358fbc63f7-1].
pool.average_kl_divergence	Calculates the average Kullback-Leibler (KL) divergence for measuring the level of disagreement in QueryByCommittee.
pool.vote_entropy	Calculates the vote entropy for measuring the level of disagreement in QueryByCommittee.
pool.variation_ratios	Calculates the variation ratios for measuring the level of disagreement in QueryByCommittee.
pool.batch_bald	BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning
pool.k_greedy_center	An active learning method that greedily forms a batch to minimize the maximum distance to a cluster center among all unlabeled datapoints.