Weighted ROC Curve in Cost Space: Extending AUC to Cost-Sensitive Learning

Authors: HuiYang Shao, Qianqian Xu, Zhiyong Yang, Peisong Wen, Gao Peifeng, Qingming Huang

NeurIPS 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We conduct extensive experiments on multiple imbalanced cost-sensitive classification tasks. The experimental results speak to the effectiveness of our proposed methods. In this section, we conduct a series of experiments for WAUC cost-sensitive learning on common long-tail benchmark datasets.
Researcher Affiliation Academia 1 Key Lab. of Intelligent Information Processing, Institute of Computing Tech., CAS 2 School of Computer Science and Tech., University of Chinese Academy of Sciences 3 BDKM, University of Chinese Academy of Sciences
Pseudocode Yes Algorithm 1 Stochastic Algorithm for WAUC Cost-sensitive Learning
Open Source Code Yes The source code is available in supplemental materials.
Open Datasets Yes We use three datasets: Binary CIFAR-10-Long-Tail Dataset [23], Binary CIFAR-100-Long-Tail Dataset [23], and Jane Street Market Prediction [14].
Dataset Splits Yes For all datasets, we divide them into the training set, validation set, and test set with a proportion 0.7:0.15:0.15.
Hardware Specification No No specific hardware details (e.g., CPU/GPU model, memory) used for running experiments were mentioned in the paper.
Software Dependencies No No specific software dependencies with version numbers (e.g., Python 3.8, PyTorch 1.9) were explicitly provided in the paper.
Experiment Setup Yes In this subsection, we show the sensitivity of β, T, and bandwidth on test data. Effect of β. Effect of T. Effect of m.