A streaming ensemble algorithm (SEA) for large-scale classification

By W. Street, YongSeog Kim. Knowledge Discovery and Data Mining, 2001

1,349 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/8fb1b96dcc133b170e7e5b340f93c5f230d495ee

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Adaptive Machine Learning for Credit Card Fraud Detection (2015, background): “If the weight of a classifier drop below a certain threshold, then the classifier is usually replaced, see for examples SEA [160] and DWM [162].”
Distribution-Free One-Pass Learning (2017, background): “- SEA [SK01] consists of three attributes x 1 , x 2 , x 3 , and 0 .”
A survey on data stream clustering and classification (2015, methodology): “[90] deployed an ensemble of classifiers for data stream.”
Credit Card Fraud Detection: A Realistic Modeling and a Novel Learning Strategy (2018, methodology): “Ensemble methods [23], [30], [43], [61], [72] and classifiers trained over a sliding window of the recent supervised samples (like STAGGER [57] and FLORA [67]) are probably the most extensively investigated passive solutions.”
Classifier Ensembles for Changing Environments (2004, background): “Street and Kim [21] consider a “quality score” for replacing a classifier in the ensemble based on its merit to the ensemble, not only on the basis of its individual accuracy.”
Learn$^{++}$ .NC: Combining Ensemble of Classifiers With Dynamically Weighted Consult-and-Vote for Efficient Incremental Learning of New Classes (2009, methodology): “online boosting [57], [58], combining single-class subnets [59], streaming ensemble algorithms (SEAs) [60], and dynamic weighted majority (DWM) [61].”
On expressiveness and uncertainty awareness in rule-based classification for data streams (2017, methodology): “• SEA artificial generator was introduced in [49] to test their stream ensemble algorithm.”
Getting the Most Out of Ensemble Selection (2006, neutral): “Note that this pruning is different from work on ensemble pruning [6, 12, 13, 14, 7].”
Collaborative filtering with temporal dynamics (2010, background): “[7, 16 , 24]) is based on maintaining an ensemble of models capable of capturing various states of the data.”
Reacting to Different Types of Concept Drift: The Accuracy Updated Ensemble Algorithm (2014, methodology): “Similar behavior was observed in figures for the SEA S and SEA F datasets, which represent scenarios with sudden concept drifts.”
A survey on concept drift adaptation (2014, methodology): “…(the combination rule may or may not change in the process); (iii) structural update where new learners are added (or existing ones are activated if they have been deactivated before) and inefficient ones are removed (or deactivated) [Kolter and Maloof 2003; Street and Kim 2001; Bouchachia 2011b].”
Learned lessons in credit card fraud detection from a practitioner perspective (2014, methodology): “Many of the techniques proposed (Chen, He, Li, & Desai, 2010; Polikar, Upda, Upda, & Honavar, 2001; Street & Kim, 2001) use ensemble classifiers in order to combine what is learnt from new observations and the knowledge acquired before.”
Adaptive Learning from Evolving Data Streams (2009, methodology): “We test on Section 6 our methods with synthetic datasets, using the SEA concepts, introduced in [ 11 ], and two sets from the UCI repository, Adult and Poker-Hand.”
Dynamic Weighted Majority: An Ensemble Method for Drifting Concepts (2007, methodology): “In previous work, we evaluated DWM using two synthetic data sets, the STAGGER concepts (Schlimmer and Granger, 1986) and the SEA concepts (Street and Kim, 2001), achieving the best published results (Kolter and Maloof, 2003).”
Tracking recurring contexts using ensemble classifiers: an application to email filtering (2009, methodology): “For classification, decisions of models in the ensemble are combined, usually with a weighted voting scheme [24, 14, 15, 9, 25, 13].”
Collaborative filtering with temporal dynamics (2009, background): “[7, 16, 24]) is based on maintaining an ensemble of models capable of capturing various states of the data.”
DDD: A New Ensemble Approach for Dealing with Concept Drift (2012, background): “Most of them are incremental learning approaches [8], [14], [15], [16], [17], [18], [19], [20], [21].”
Classifier Ensembles for Detecting Concept Change in Streaming Data: Overview and Perspectives (2008, methodology): “Included in this group are most ensemble methods for changing environments: Winnow variants [24, 28], AdaBoost variants [5, 30], “replace-the-loser” approaches [21,22,34,35,39].”
A framework for generating data to simulate changing environments (2007, background): “Online learning is increasingly occupying centre stage in data mining as more and more applications generate massive streams of data [5, 6, 29].”
Learning under Concept Drift: an Overview (2010, background): “Often these blocks are non overlapping [142, 150, 148, 7, 115, 72, 81, 79, 95], sometimes overlapping [44].”