Pruning a Random Forest by Learning a Learning Algorithm

Dheenadayalan, Kumar; Srinivasaraghavan, G.; Muralidhara, V. N.

doi:10.1007/978-3-319-41920-6_41

Cited by 6 publications

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, ARF (Ye et al , 2017) has fewer errors and more stability than classical RF, same thing, (Yang et al , 2016) presents improved random forests (IRF) which increases the resistance of RF and improves prediction accuracy. There is also another work (Jiang et al , 2017) that presents a new pruning method based on the importance of tree branches, and this type of method can improve the accuracy of the classical RF (Dheenadayalan et al , 2016), and reduce, in particular, the size of the tree, and in general size of the RF.…”

Section: Related Workmentioning

confidence: 99%

Big Data analytics for prediction: parallel processing of the big learning base with the possibility of improving the final result of the prediction

Djafri

Bensaber

Adjoudj

2018

IDD

View full text Add to dashboard Cite

Purpose This paper aims to solve the problems of big data analytics for prediction including volume, veracity and velocity by improving the prediction result to an acceptable level and in the shortest possible time. Design/methodology/approach This paper is divided into two parts. The first one is to improve the result of the prediction. In this part, two ideas are proposed: the double pruning enhanced random forest algorithm and extracting a shared learning base from the stratified random sampling method to obtain a representative learning base of all original data. The second part proposes to design a distributed architecture supported by new technologies solutions, which in turn works in a coherent and efficient way with the sampling strategy under the supervision of the Map-Reduce algorithm. Findings The representative learning base obtained by the integration of two learning bases, the partial base and the shared base, presents an excellent representation of the original data set and gives very good results of the Big Data predictive analytics. Furthermore, these results were supported by the improved random forests supervised learning method, which played a key role in this context. Originality/value All companies are concerned, especially those with large amounts of information and want to screen them to improve their knowledge for the customer and optimize their campaigns.

show abstract

Section: Related Workmentioning

confidence: 99%

Big Data analytics for prediction: parallel processing of the big learning base with the possibility of improving the final result of the prediction

Djafri

Bensaber

Adjoudj

2018

IDD

View full text Add to dashboard Cite

show abstract

“…There have been many recent works to improve the performance of random forests: [36] proposes pruning nodes for efficient learning, [37] presents incremental modeling for large scale recognition, and [38] investigates how to tune the number of trees. SVM [39,40] or random projection [41,42] is often used as the binary classifier for better node split.…”

Section: Random Forest As An Ensemble Learning Methodsmentioning

confidence: 99%

Collaborative Training of Balanced Random Forests for Open Set Domain Adaptation

Ryu¹,

Bae²,

Lim³

2020

Preprint

View full text Add to dashboard Cite

In this paper, we introduce a collaborative training algorithm of balanced random forests for domain adaptation tasks which can avoid the overfitting problem. In real scenarios, most domain adaptation algorithms face the challenges from noisy, insufficient training data. Moreover in open set categorization, unknown or misaligned source and target categories adds difficulty. In such cases, conventional methods suffer from overfitting and fail to successfully transfer the knowledge of the source to the target domain. To address these issues, the following two techniques are proposed. First, we introduce the optimized decision tree construction method, in which the data at each node are split into equal sizes while maximizing the information gain. Compared to the conventional random forests, it generates larger and more balanced decision trees due to the even-split constraint, which contributes to enhanced discrimination power and reduced overfitting. Second, to tackle the domain misalignment problem, we propose the domain alignment loss which penalizes uneven splits of the source and target domain data. By collaboratively optimizing the information gain of the labeled source data as well as the entropy of unlabeled target data distributions, the proposed CoBRF algorithm achieves significantly better performance than the state-of-the-art methods. The proposed algorithm is extensively evaluated in various experimental setups in challenging domain adaptation tasks with noisy and small training data as well as open set domain adaptation problems, for two backbone networks of AlexNet and ResNet-50.

show abstract

“…Our approach is closely related to ensemble pruning [TPV09, GRF00, DSM16, ZZY17]. In this method, an ensemble size of classifiers is reduced to increase model efficiency and predictive performance [BBSH14].…”

Section: Data Aggregation For the Visualizationmentioning

confidence: 99%

RfX: A Design Study for the Interactive Exploration of a Random Forest to Enhance Testing Procedures for Electrical Engines

Eirich

Munch

Jäckle

et al. 2022

Computer Graphics Forum

View full text Add to dashboard Cite

Random Forests (RFs) are a machine learning (ML) technique widely used across industries. The interpretation of a given RF usually relies on the analysis of statistical values and is often only possible for data analytics experts. To make RFs accessible to experts with no data analytics background, we present RfX, a Visual Analytics (VA) system for the analysis of a RF's decisionmaking process. RfX allows to interactively analyse the properties of a forest and to explore and compare multiple trees in a RF. Thus, its users can identify relationships within a RF's feature subspace and detect hidden patterns in the model's underlying data. We contribute a design study in collaboration with an automotive company. A formative evaluation of RFX was carried out with two domain experts and a summative evaluation in the form of a field study with five domain experts. In this context, new hidden patterns such as increased eccentricities in an engine's rotor by observing secondary excitations of its bearings were detected using analyses made with RfX. Rules derived from analyses with the system led to a change in the company's testing procedures for electrical engines, which resulted in 80% reduced testing time for over 30% of all components.

show abstract

Pruning a Random Forest by Learning a Learning Algorithm

Cited by 6 publications

References 16 publications

Big Data analytics for prediction: parallel processing of the big learning base with the possibility of improving the final result of the prediction

Big Data analytics for prediction: parallel processing of the big learning base with the possibility of improving the final result of the prediction

Collaborative Training of Balanced Random Forests for Open Set Domain Adaptation

RfX: A Design Study for the Interactive Exploration of a Random Forest to Enhance Testing Procedures for Electrical Engines

Contact Info

Product

Resources

About