Corruption Robust Active Learning

Authors: Yifang Chen, Simon S. Du, Kevin G. Jamieson

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

Reproducibility Variable Result LLM Response
Research Type Theoretical We conduct theoretical studies on streaming-based active learning for binary classification under unknown adversarial label corruptions.
Researcher Affiliation Academia Yifang Chen, Simon S. Du, Kevin Jamieson Paul G. Allen School of Computer Science & Engineering University of Washington, Seattle,WA {yifangc, ssdu, jamieson }@cs.washington.edu
Pseudocode Yes Algorithm 1 Robust CAL (modified the elimination condition)
Open Source Code No The paper does not contain any explicit statements about releasing source code for their proposed method or experiments.
Open Datasets No This is a theoretical paper that does not describe experiments run on specific datasets for training. It discusses theoretical concepts of samples and label complexity.
Dataset Splits No This is a theoretical paper and does not describe any dataset splits for experimental validation.
Hardware Specification No This is a theoretical paper and does not describe any hardware used for running experiments.
Software Dependencies No This is a theoretical paper and does not mention specific software dependencies with version numbers used for running experiments.
Experiment Setup No This is a theoretical paper and does not describe an experimental setup with hyperparameters or system-level training settings.