Adaptive Sampling with Optimal Cost for Class-Imbalance Learning
Authors: Yuxin Peng
AAAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | The solid experiments are conducted to compare the performance between the proposed approach and 12 state-of-the-art methods on challenging 16 UCI data sets on 3 evaluation metrics, and the results show the proposed approach can achieve superior performance in class-imbalance learning. |
| Researcher Affiliation | Academia | Institute of Computer Science and Technology, Peking University, Beijing 100871, China pengyuxin@pku.edu.cn |
| Pseudocode | Yes | Algorithm 1: Calculate the weight of training data and Algorithm 2: Select the Best Cost Ratio |
| Open Source Code | No | The paper does not provide an explicit statement about the release of source code or a link to a code repository. |
| Open Datasets | Yes | In the experiments, the 16 UCI data sets (Frank, & Asuncion 1998) are adopted to evaluate the proposed approach. [...] Frank, A., and Asuncion, A. 1998. UCI Machine Learning Repository. CA: University of California, Irvine, School of Information and Computer Science, http://archive.ics.uci.edu/ml. |
| Dataset Splits | Yes | For each data set, a ten-fold stratified cross validation is performed, and for each fold, the classification is repeated for ten times to reduce the influence of randomness. The whole cross validation process is repeated for five times to avoid any bias that may occur in random selection. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., GPU/CPU models, memory amounts) used for running its experiments. |
| Software Dependencies | No | In all above methods, for each subset of the training data, SVM is used to train a sub-classifier with the Lib SVM implementation, RBF kernel and default parameters. |
| Experiment Setup | Yes | In all above methods, for each subset of the training data, SVM is used to train a sub-classifier with the Lib SVM implementation, RBF kernel and default parameters. [...] Algorithm 2: Select the Best Cost Ratio, Initialize: Best Accuracy 0 Imb Ratio |Ni| / (j+1)|P| Max Cost 2 Imb Ratio k 0 repeat 1. k k+1 2. Curr Cost Max Cost T (k-1)/(T-1) |