Scalable and Parallel Boosting with MapReduce

Palit, Indranil; Reddy, Chandan K.

doi:10.1109/tkde.2011.208

Cited by 84 publications

(44 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to obtain the exact solution, all nodes in the cluster are required to evaluate the potential split points found by all other nodes. Palit and Reddy [98] utilize the MapReduce framework for developing two parallel boosting algorithms: AdaBoost.PL and LogitBoost.PL which are competitive to their corresponding serial versions in terms of predicative performance. Theses algorithms need only one cycle of MapReduce to complete the algorithms.…”

Section: Scaling Up Decision Forests Methodsmentioning

confidence: 99%

Decision forest: Twenty years of research

2016

View full text Add to dashboard Cite

Section: Scaling Up Decision Forests Methodsmentioning

confidence: 99%

Decision forest: Twenty years of research

2016

View full text Add to dashboard Cite

“…Furthermore, several MapReduce implementations have been proposed for different classification algorithms such as cost-sensitive fuzzy rule based systems for imbalanced classification, 17 ensembles of classifiers 18,19 or Support Vector Machines 20 to mention a few.…”

Section: Mapreduce Programming Modelmentioning

confidence: 99%

A MapReduce Approach to Address Big Data Classification Problems Based on the Fusion of Linguistic Fuzzy Rules

Río¹,

López²,

Benítez³

et al. 2015

IJCIS

View full text Add to dashboard Cite

The big data term is used to describe the exponential data growth that has recently occurred and represents an immense challenge for traditional learning techniques. To deal with big data classification problems we propose the Chi-FRBCS-BigData algorithm, a linguistic fuzzy rule-based classification system that uses the MapReduce framework to learn and fuse rule bases. It has been developed in two versions with different fusion processes. An experimental study is carried out and the results obtained show that the proposal is able to handle these problems providing competitive results.

show abstract

“…Two parallel boosting algorithms, AD-ABOOST.PL and LOGITBOOST.PL were proposed by Indranil et al [9] which facilitate simultaneous participation of multiple computing nodes to construct a boosted ensemble classifier. These algorithms achieve a significant speedup and still are competitive to the corresponding serial versions in terms of the generalization performance.…”

Section: Related Workmentioning

confidence: 99%

Labeling Instances in Evolving Data Streams with MapReduce

Haque

Parker

Khan

2013

2013 IEEE International Congress on Big Data

View full text Add to dashboard Cite

Unlike traditional data mining where data is static, mining algorithms for data streams must process the data "on the fly" and update the class decision boundaries as the stream progresses to address the challenges of concept drift and feature evolution. In our current work, we have proposed a multi-tiered ensemble based fast and robust method, which rapidly learns the concepts in a data stream, predicts labels for new data with strong accuracy, and agilely tracks the dynamic changes in the evolving concepts and feature space. Bottleneck of our current work is, it needs to build ADABOOST ensemble for each numeric feature. This can face scalability issue as number of features can be very large at times in data stream. In this paper we propose a method to parallelize the independent parts of that work using a MapReduce framework. This increases scalability and achieves a significant speedup without compromising classification accuracy. We demonstrate the performance of our approach in terms of speedup, scaleup and classification accuracy.

show abstract

Scalable and Parallel Boosting with MapReduce

Cited by 84 publications

References 25 publications

Decision forest: Twenty years of research

Decision forest: Twenty years of research

A MapReduce Approach to Address Big Data Classification Problems Based on the Fusion of Linguistic Fuzzy Rules

Labeling Instances in Evolving Data Streams with MapReduce

Contact Info

Product

Resources

About