Transfer Learning on Decision Tree with Class Imbalance

Minvielle, Ludovic; Atiq, Mounir; Peignier, Sergio; Mougeot, Mathilde

doi:10.1109/ictai.2019.00141

Cited by 11 publications

(13 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, Al-Stouhi et al previously proposed that transfer learning can be used to solve class imbalance problems with inadequate data and provided theoretical and empirical validation on healthcare and text classification applications [ 10 ]. Minvielle et al explored the impact of class imbalance using transfer learning on decision trees [ 33 ]. However, only a few studies have been carried out on AMR so far.…”

Section: Discussionmentioning

confidence: 99%

“…Park et al used meta-transfer learning to explore the data heterogeneity and extremely small sample size problem based on single cell data [ 30 ]. Transfer learning is also widely used in the medical area with an imbalanced label [ 10 , 31 , 32 , 33 , 34 ]. For example, Gao et al used deep transfer learning to reduce healthcare disparities arising from imbalanced biomedical data [ 35 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Transfer Learning Enables Robust Prediction of Antimicrobial Resistance for Novel Antibiotics

et al. 2022

View full text Add to dashboard Cite

Antimicrobial resistance (AMR) has become one of the serious global health problems, threatening the effective treatment of a growing number of infections. Machine learning and deep learning show great potential in rapid and accurate AMR predictions. However, a large number of samples for the training of these models is essential. In particular, for novel antibiotics, limited training samples and data imbalance hinder the models’ generalization performance and overall accuracy. We propose a deep transfer learning model that can improve model performance for AMR prediction on small, imbalanced datasets. As our approach relies on transfer learning and secondary mutations, it is also applicable to novel antibiotics and emerging resistances in the future and enables quick diagnostics and personalized treatments.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Deep Transfer Learning Enables Robust Prediction of Antimicrobial Resistance for Novel Antibiotics

et al. 2022

View full text Add to dashboard Cite

show abstract

“…If topology changes are considered, they can be included in the input features [16,32], such as those indicating whether transmission lines are available or not [16]. Alternatively, transfer learning on decision trees [33,34] can be adopted to modify the tree structure or thresholds.…”

Section: Model-based Solution Of Multiple Corrective Sced Runsmentioning

confidence: 99%

“…of testing instances × 100%. (33) Results are summarized in Table 5. CART has a TPR of 98.87% and a TIR of 94.17%, and 139 unpredicted contingencies from 85 instances (a contingency c may be counted multiple times as unpredicted from different instances).…”

Section: No Of Instances With All Predictedmentioning

confidence: 99%

Interpretable data‐driven contingency classification for real‐time corrective security‐constrained economic dispatch

Yu,

Gao,

et al. 2023

IET Renewable Power Gen

View full text Add to dashboard Cite

High penetrations of renewable energy are crucial for low‐carbon power systems. However, the higher volatility of renewable power generation pushes real‐time operations closer to equipment limits. It is thus important to utilize flexibilities in the system through corrective security‐constrained economic dispatch (SCED) that allows generators to take corrective adjustments after contingencies. The corrective SCED problem, containing a large number of contingencies, and corresponding post‐contingency decisions and constraints, is very large in scale and difficult to solve using purely model‐based methods within the strict time limits of real‐time markets. To accelerate the solution process, this paper develops a novel interpretable data‐driven contingency classification method. Historical data and their potentially useful patterns are utilized in interpretable data‐driven decision tree classifiers. To directly consider continuous features, such as net load values, and to consider imbalanced datasets without much additional complexity, Improved Strong Optimal Classification Trees (ISOCTs) are developed with new branching threshold constraints and category weights in the objective function. ISOCTs are then embedded into a hybrid model‐based and data‐driven framework to guarantee the accuracy of the real‐time active contingency set and the resulting security of dispatch decisions. Numerical testing results demonstrate the classification accuracy, computational efficiency, and interpretability of the proposed approach.

show abstract

“…Liu et al 27 treated synthetic minority samples as additional source data and extracted knowledge from them to enrich the target minority class. Minvielle et al 28 analyzed the impact of class imbalance on two TL methods based on decision trees, and proposed an improvement for each of them, termed as

{\text{SER}}^{* }

and

{\text{STRUT}}^{* }

. Motivated by the superior performance of TL in handling imbalanced data sets, we present a transfer weighted‐ELM (TWELM)‐based class imbalance learning, in which a WELM output matrix is learned from the labeled data in source domain and treated as a regularization term to improve the performance of a target classifier.…”

Section: Introductionmentioning

confidence: 99%

A transfer weighted extreme learning machine for imbalanced classification

Guo

Jiao

Tan

et al. 2022

Int J of Intelligent Sys

View full text Add to dashboard Cite

Previous class imbalance learning methods are mostly grounded on the assumption that all training data have been labeled, however, is impractical in many real-world applications. The limited amount of labeled instances may produce a classifier with poor generalization. To address the issue, a transfer weighted extreme learning machine (TWELM) classifier is proposed, with the purpose of extracting knowledge from other domains to improve the classification performance of a classifier in a limited labeled target domain. To be specific, a well-tuned weighted extreme learning machine classifier is first learned from source data that has been completely labeled. Subsequently, another extreme learning machine classifier is obtained from the limited labeled target domain data to preserve the target domain structural knowledge and the decision boundary information. Finally, the target classifier

show abstract

Transfer Learning on Decision Tree with Class Imbalance

Cited by 11 publications

References 17 publications

Deep Transfer Learning Enables Robust Prediction of Antimicrobial Resistance for Novel Antibiotics

Deep Transfer Learning Enables Robust Prediction of Antimicrobial Resistance for Novel Antibiotics

Interpretable data‐driven contingency classification for real‐time corrective security‐constrained economic dispatch

A transfer weighted extreme learning machine for imbalanced classification

Contact Info

Product

Resources

About