Cost-Sensitive Feature Selection via F-Measure Optimization Reduction
Authors: Meng Liu, Chang Xu, Yong Luo, Chao Xu, Yonggang Wen, Dacheng Tao
AAAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experimental results conducted on synthetic, multi-class and multi-label datasets validate the efficiency and significance of our feature selection method. |
| Researcher Affiliation | Academia | Key Laboratory of Machine Perception (MOE), Cooperative Medianet Innovation Center, School of Electronics Engineering and Computer Science, PKU, Beijing 100871, China Centre for Artificial Intelligence, UTS, Sydney, NSW 2007, Australia School of Computer Science and Engineering, NTU, 639798, Singapore |
| Pseudocode | Yes | Algorithm 1 An iterative algorithm to solve the optimization problem in Eq. (10). |
| Open Source Code | No | The paper does not provide an explicit statement about the availability of open-source code for the methodology described, nor does it provide a link to a repository. |
| Open Datasets | Yes | For multi-class classification, we use two datasets: handwritten digit dataset USPS2 and face image dataset Yale B2. For multi-label classification, we use MSVCv23 and TRECVID20054 datasets. ... 2http://www.cad.zju.edu.cn/home/dengcai/Data/MLData.html 3http://research.microsoft.com/en-us/projects/ objectclassrecognition/ 4http://www-nlpir.nist.gov/projects/tv2005/ |
| Dataset Splits | Yes | For each dataset, we randomly select 1/3 of the training samples for validation to tune the hyperparameters. For datasets that do not have a separate test set, the data is first split to keep 1/4 for testing. ... We repeat the experiments 10 times with random seeds for generating the validation sets. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., CPU/GPU models, memory, or cloud instances) used for running the experiments. |
| Software Dependencies | No | The paper mentions 'SVM with linear kernel and parameter C = 1' but does not specify software names with version numbers for reproducibility (e.g., Python, scikit-learn, PyTorch versions). |
| Experiment Setup | Yes | During the training process, the parameter λ in our method is optimized in the range of {10 6, 10 5, . . . , 106}, and the number of selected features is set as {20, 30, . . . , 120}. To fairly compare all different feature selection methods, classification experiments are conducted on all datasets using 5-fold cross validation SVM with linear kernel and parameter C = 1. |