Understanding Instance-Level Label Noise: Disparate Impacts and Treatments

Authors: Yang Liu

ICML 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We simulate a 2D example: there are two classes of instances. The outer annulus represents one class and the inner ball is the other. Given the plotted training data, we train a 2-layer neural network using the cross-entropy (CE) loss. ... We further illustrate this in Figure 3 where we train a neural network on the CIFAR-10 dataset with synthesized noisy labels.
Researcher Affiliation Academia 1Department of Computer Science and Engineering, University of California, Santa Cruz, CA, USA. Correspondence to: Yang Liu <yangliu@ucsc.edu>.
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide concrete access to source code for the methodology described.
Open Datasets Yes Figure 1 shows a collection of 10 similar Cats" from the CIFAR-10 dataset (Krizhevsky et al., 2009). ... Figure 3 where we train a neural network on the CIFAR-10 dataset with synthesized noisy labels.
Dataset Splits No The paper does not provide specific dataset split information (e.g., percentages, sample counts) for training, validation, or testing.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details (e.g., library or solver names with version numbers).
Experiment Setup No The paper mentions training a '2-layer neural network using the cross-entropy (CE) loss' but does not provide specific hyperparameters (e.g., learning rate, batch size, number of epochs) or detailed training configurations in the main text.