Combining Active Learning and Self-Labeling for Data Stream Mining

Korycki, Łukasz; Krawczyk, Bartosz

doi:10.1007/978-3-319-59162-9_50

Cited by 12 publications

(12 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Bouguelia et al [11] proposed a new query strategy based on instance weighting, but the time complexity of the weigh calculation was relatively high. Korycki and Krawczyk [31] applied an active learning strategy to classify data streams and combine it with the self-labeling approach.…”

Section: Active Learning Methods For Data Stream Classificationmentioning

confidence: 99%

Active Weighted Aging Ensemble for Drifted Data Stream Classification

Woźniak¹,

Zyblewski²,

Ksieniewicz³

2021

Preprint

View full text Add to dashboard Cite

One of the significant problems of streaming data classification is the occurrence of concept drift, consisting of the change of probabilistic characteristics of the classification task. This phenomenon destabilizes the performance of the classification model and seriously degrades its quality. An appropriate strategy counteracting this phenomenon is required to adapt the classifier to the changing probabilistic characteristics. One of the significant problems in implementing such a solution is the access to data labels. It is usually costly, so to minimize the expenses related to this process, learning strategies based on semisupervised learning are proposed, e.g., employing active learning methods indicating which of the incoming objects are valuable to be labeled for improving the classifier's performance. This paper proposes a novel chunk-based method for non-stationary data streams based on classifier ensemble learning and an active learning strategy considering a limited budget that can be successfully applied to any data stream classification algorithm. The proposed method has been evaluated through computer experiments using both real and generated data streams. The results confirm the high quality of the proposed algorithm over state-of-the-art methods.

show abstract

Section: Active Learning Methods For Data Stream Classificationmentioning

confidence: 99%

Active Weighted Aging Ensemble for Drifted Data Stream Classification

Woźniak¹,

Zyblewski²,

Ksieniewicz³

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…It is described as a highly scalable, parallelizable and optimized online Bayesian framework using sequential Monte Carlo and so-called gap assumption. In our previous work, we have proposed the first study on a combination of active and self-labeling solutions for data streams [23]. However, the algorithm described there used a fixed threshold and therefore was unable to efficiently adapt to the presence of concept drift.…”

Section: Labeling Constraints In Data Streamsmentioning

confidence: 99%

Mining Drifting Data Streams on a Budget: Combining Active Learning with Self-Labeling

Korycki¹,

Krawczyk²

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Mining data streams poses a number of challenges, including the continuous and non-stationary nature of data, the massive volume of information to be processed and constraints put on the computational resources. While there is a number of supervised solutions proposed for this problem in the literature, most of them assume that access to the ground truth (in form of class labels) is unlimited and such information can be instantly utilized when updating the learning system. This is far from being realistic, as one must consider the underlying cost of acquiring labels. Therefore, solutions that can reduce the requirements for ground truth in streaming scenarios are required. In this paper, we propose a novel framework for mining drifting data streams on a budget, by combining information coming from active learning and self-labeling. We introduce several strategies that can take advantage of both intelligent instance selection and semi-supervised procedures, while taking into account the potential presence of concept drift. Such a hybrid approach allows for efficient exploration and exploitation of streaming data structures within realistic labeling budgets. Since our framework works as a wrapper, it may be applied with different learning algorithms. Experimental study, carried out on a diverse set of real-world data streams with various types of concept drift, proves the usefulness of the proposed strategies when dealing with highly limited access to class labels. The presented hybrid approach is especially feasible when one cannot increase a budget for labeling or replace an inefficient classifier. We deliver a set of recommendations regarding areas of applicability for our strategies.

show abstract

“…This may be prohibitive in many streaming scenarios, especially if we add the fundamental cluster and smoothness requirements. In fact, results from some publications suggest that either feasible improvements from unlabeled data are barely significant or very unstable and highly dependent on characteristics of a specific stream [51].…”

Section: Limited Budget and Underfittingmentioning

confidence: 99%

“…Thus, the very few labeled objects we obtain are essential for keeping our models up-to-date and we should exploit them as much as possible to avoid the waste of potential benefits. Finally, since active learning methods can be seen as exploration methods and semi-supervised ones as regularization-exploitation, approaches combining both of them are a promising research direction [48,51]. However, due to the mentioned problems with dynamic environments and using unsupervised input, in this work, we focus on investigating how significant improvements can be obtained solely from the exploitation of scare but reliable supervised information, provided with actively selected instances.…”

Section: Limited Budget and Underfittingmentioning

confidence: 99%

Instance exploitation for learning temporary concepts from sparsely labeled drifting data streams

Korycki¹,

Krawczyk²

2020

Preprint

Self Cite

View full text Add to dashboard Cite

Continual learning from streaming data sources becomes more and more popular due to the increasing number of online tools and systems. Dealing with dynamic and everlasting problems poses new challenges for which traditional batch-based offline algorithms turn out to be insufficient in terms of computational time and predictive performance. One of the most crucial limitations is that we cannot assume having access to a finite and complete data set -we always have to be ready for new data that may complement our model. This poses a critical problem of providing labels for potentially unbounded streams. In the real world, we are forced to deal with very strict budget limitations, therefore, we will most likely face the scarcity of annotated instances, which are essential in supervised learning. In our work, we emphasize this problem and propose a novel instance exploitation technique. We show that when: (i) data is characterized by temporary non-stationary concepts, and (ii) there are very few labels spanned across a long time horizon, it is actually better to risk overfitting and adapt models more aggressively by exploiting the only labeled instances we have, instead of sticking to a standard learning mode and suffering from severe underfitting. We present different strategies and configurations for our methods, as well as an ensemble algorithm that attempts to maintain a sweet spot between risky and normal adaptation. Finally, we conduct a complex in-depth comparative analysis of our methods, using state-of-the-art streaming algorithms relevant to the given problem.

show abstract

Combining Active Learning and Self-Labeling for Data Stream Mining

Cited by 12 publications

References 12 publications

Active Weighted Aging Ensemble for Drifted Data Stream Classification

Active Weighted Aging Ensemble for Drifted Data Stream Classification

Mining Drifting Data Streams on a Budget: Combining Active Learning with Self-Labeling

Instance exploitation for learning temporary concepts from sparsely labeled drifting data streams

Contact Info

Product

Resources

About