Contrastive Label Enhancement

Authors: Yifei Wang, Yiyang Zhou, Jihua Zhu, Xinyuan Liu, Wenbiao Yan, Zhiqiang Tian

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

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on LDL benchmark datasets demonstrate the effectiveness and superiority of our method.
Researcher Affiliation Academia School of Software Engineering, Xi an Jiaotong University, Xi an, China
Pseudocode Yes Algorithm 1 The optimization of Con LE
Open Source Code No The paper does not provide concrete access to source code (specific repository link, explicit code release statement, or code in supplementary materials) for the methodology described.
Open Datasets Yes SJAFFE dataset [Lyons et al., 1998] and SBU-3DFE dataset [Yin et al., 2006] are obtained from the two facial expression databases, JAFFE and BU-3DFE. ... Yeast datasets are derived from biological experiments on gene expression levels of budding yeast at different time points [Eisen et al., 1998].
Dataset Splits Yes All algorithms are evaluated by ten times ten-fold cross-validation for fairness.
Hardware Specification Yes The code of this method is implemented by Py Torch [Paszke et al., 2019] on one NVIDIA Geforce GTX 2080ti GPU with 11GB memory.
Software Dependencies No The paper mentions "Py Torch [Paszke et al., 2019]" but does not specify a precise version number (e.g., 1.x.x) for reproducibility. It also mentions "SGD optimizer [Ruder, 2016]" and "Leaky Re LU activation function [Maas et al., 2013]" without version numbers.
Experiment Setup Yes When comparing with other algorithms, the hyperparameters of Con LE are set as follows: λ1 is set to 0.5, λ2 is set to 1 and the temperature parameter τI is 0.5.