Ensemble Methods: Foundations and Algorithms

By D. Van. 2012

How researchers see this paper

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

Citations in the corpus

Learning Optimal Decision Trees with MaxSAT and its Integration in AdaBoost (2020, neutral): “Ensemble methods is a set of methods that train multiple learners and then combine them for getting better predictions than a single classiﬁer [ Zhou, 2012 ] .”
Ensemble Methods for Causal Effects in Panel Data Settings (2019, background): “ing. In many prediction problems researchers have found that combinations of prediction methods (“ensembles”) perform better than individual methods (Hal Varian, 2014; James Surowiecki, 2005; Zhi-Hua Zhou, 1983). A simple example is random forests, which combines predictions from many regression tre”
FOSTER: Feature Boosting and Compression for Class-Incremental Learning (2022, background): “Boosting represents a family of machine learning algorithms that convert weak learners to strong ones [50].”
A review of ensemble learning and data augmentation models for class imbalanced problems: combination, implementation and evaluation (2023, methodology): “The term boosting refers to a family of algorithms that are able to convert weak learners to strong learners [50].”
A Survey on Ensemble Learning for Data Stream Classification (2017, methodology): “We refer readers to chapter 8 of Kuncheva’s book [Kuncheva 2004b] and other works [Kuncheva and Whitaker 2003; Banﬁeld et al. 2005; Zhou 2012] for an extensive discussion of diversity measures for ensemble learners.”
Model recommendation: Generating object detectors from few samples (2015, background): “One extension is to jointly recommend sets of models as in ensemble learning [58] and mixture of experts [19].”
Comparing Recognition Performance and Robustness of Multimodal Deep Learning Models for Multimodal Emotion Recognition (2021, methodology): “Ensemble learning is often used to assemble these classifiers [37].”
Weighted Oblique Decision Trees (2019, methodology): “…developed in the literature (Domingos and Hulten 2000; Zhou and Chen 2002; Geurts, Ernst, and Wehenkel 2006; Shotton et al. 2013a; Abuzaid et al. 2016), and decision trees have been used as base learners for ensemble algorithms such as boosting and bagging (Breiman 2001; Friedman 2001; Zhou 2012).”
Domain Adaptive Ensemble Learning (2020, methodology): “Ensemble methods have been extensively researched in the machine learning community [65].”
Neural Networks and Deep Learning (2018, unknown): “Detailed discussions of ensemble methods for classification may be found in [438, 566].”
Fully automatic acute ischemic lesion segmentation in DWI using convolutional neural networks (2017, unknown): “An ensemble of all CNNs therefore benefits for performance improvement because of their accuracy and diversity (Zhou, 2012).”
A brief introduction to weakly supervised learning (2018, methodology): “The fundamental strategy tomake semi-supervised learning ‘safer’ is to optimize the worst-case performance among the options, possibly by incorporating ensemble mechanisms [35].”
Collaborative Unsupervised Domain Adaptation for Medical Image Diagnosis (2019, methodology): “MobileNet [60] 39.85 77.51 62.95 40.80 30.63 33.91 47.61 37.33 75.88 62.74 32.83 28.39 32.11 45.38 MentorNet [33] 34.98 69.60 68.40 44.40 38.07 38.25 48.95 35.62 64.95 63.47 42.04 36.00 36.00 46.34 Co-teaching [22] 42.96 70.38 78.89 47.01 40.24 40.87 53.39 43.59 69.26 69.56 41.18 38.02 39.06 50.11 N”
One-Pass Learning with Incremental and Decremental Features (2016, methodology): “To integrate two classifiers hðsÞ and h, we combine two classifiers like ensemble methods [17].”
Learnware: on the future of machine learning (2016, methodology): “In such cases, ensemble methods [10] that combine multiple models to use may offer some solutions, just like the description of reusable ensemble [10, pp.”
Human action recognition using genetic algorithms and convolutional neural networks (2016, methodology): “An overview of ensemble methods is given in [67].”
Complete Random Forest Based Class Noise Filtering Learning for Improving the Generalizability of Classifiers (2019, methodology): “The sampling methods reduce the number of features for establishing a decision tree so that the overfitting can be decreased [61], [62], [63].”
Binary relevance for multi-label learning: an overview (2018, background): “It is worth noting that stacking aggregation employs ensemble learning [52] to combine two sets of binary relevance models with deterministic label correlation exploitation.”