Label Propagation with Weak Supervision

Authors: Rattana Pukdee, Dylan Sam, Pradeep Kumar Ravikumar, Nina Balcan

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

Reproducibility Variable Result LLM Response
Research Type Experimental We provide experimental results on standard weakly supervised benchmark tasks (Zhang et al., 2021) to support our theoretical claims and to compare our methods to standard LPA, other semi-supervised methods, and existing weakly supervised baselines. Our experiments demonstrate that incorporating smoothness via LPA in the standard weakly supervised pipeline leads to better performance, outperforming many existing WSL algorithms.
Researcher Affiliation Academia Machine Learning Department Carnegie Mellon University Pittsburgh, USA {rpukdee , dylansam}@cs.cmu.edu
Pseudocode No The paper does not contain any clearly labeled "Pseudocode" or "Algorithm" blocks or figures.
Open Source Code Yes Code to replicate our experiments can be found here1. 1https://github.com/dsam99/label propagation weak supervision
Open Datasets Yes We compare our approaches to existing weak supervision methods, standard LPA, and other semi-supervised baselines on 4 binary classification datasets from the WRENCH benchmark (Zhang et al., 2021).
Dataset Splits Yes To generate a small set of labeled data, we randomly sample n = 100 points from the training data. The remaining data serves as our unlabeled training data. We perform hyperparameter optimization of all methods, selecting the best set of parameters on the validation set.
Hardware Specification Yes We use a single GPU (NVIDIA Ge Force RTX 2080Ti) to run our methods and each of the baselines.
Software Dependencies No The paper mentions software tools like "Snorkel Me Ta L", "BERT", and "Res Net" but does not provide specific version numbers for these or any other software dependencies, nor does it specify programming language versions.
Experiment Setup Yes We optimize over the following parameters for all methods endmodels: learning rate: [0.01, 0.001, 0.0001] number of epochs: [20, 30, 40, 50] weight decay: [0, 0.01, 0.001] In each experiment, we have a fixed batch size of 100 and a fixed architecture of a 2 layer neural network with a hidden dimension of 64 and a Re LU activation function.