Partial Label Learning via Label Influence Function

Authors: Xiuwen Gong, Dong Yuan, Wei Bao

ICML 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments conducted on various datasets demonstrate the superiorities of the proposed methods in terms of prediction accuracy, which in turn validates the effectiveness of the proposed PLL-IF framework.
Researcher Affiliation Academia 1Faculty of Engineering, The University of Sydney, NSW, Australia.
Pseudocode Yes Algorithm 1 CG Algorithm
Open Source Code No The paper does not contain any statement or link indicating that the source code for their methodology is publicly available.
Open Datasets Yes We conducted controlled experiments on synthetic PLL datasets configured from six UCI datasets1... and We also conducted experiments on six real-world PLL datasets, which are summarized in Table 2.
Dataset Splits Yes For the evaluation metric, we perform five-fold cross-validation on each dataset and report the mean accuracy with standard deviation of each method.
Hardware Specification No The paper does not provide specific details about the hardware used for running experiments.
Software Dependencies No The paper mentions software like LIBLINEAR and PyTorch, but does not provide specific version numbers for these or other dependencies required for reproducibility.
Experiment Setup Yes Specifically, we employ a 3-layer neural network for the proposed PLL-IF+NN, and use the Leaky Re Lu activation function in the two middle layers with 512 and 256 hidden units respectively and employ softmax function in the output layer. The optimizer is Adam (Kingma & Ba, 2015) with the initial learning rate to be 0.0001. The mini-batch size is set to 32 and we train the model 500 epochs with crossentropy loss and update ground-truth label variable every epoch.