Trade-offs and Guarantees of Adversarial Representation Learning for Information Obfuscation

Authors: Han Zhao, Jianfeng Chi, Yuan Tian, Geoffrey J. Gordon

NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We conduct experiments on two real-world datasets to corroborate the inference guarantees and validate this trade-off.
Researcher Affiliation Collaboration Han Zhao D. E. Shaw & Co. han.zhao@cs.cmu.edu Jianfeng Chi Department of Computer Science University of Virginia jc6ub@virginia.edu Yuan Tian Department of Computer Science University of Virginia yuant@virginia.edu Geoffrey J. Gordon Carnegie Mellon University Microsoft Research Montreal geoff.gordon@microsoft.com
Pseudocode No The paper does not contain any clearly labeled pseudocode or algorithm blocks.
Open Source Code No The paper does not provide an explicit statement or link for the open-source code of the methodology described.
Open Datasets Yes (1) Adult dataset [8]: The Adult dataset is a benchmark dataset for classification. (2) UTKFace dataset [38]: The UTKFace dataset is a large-scale face benchmark dataset containing more than 20,000 images with annotations of age, gender, and ethnicity. [8] links to UCI machine learning repository, and [38] refers to a published paper from which the dataset originates.
Dataset Splits No The paper states, 'We refer readers to Sec. C in the appendix for detailed descriptions about the data pre-processing pipeline and the data distribution for each dataset.' However, it does not provide specific split percentages or sample counts for training, validation, or test sets within the main text.
Hardware Specification No The acknowledgements mention 'a Nvidia GPU grant' but do not specify any particular GPU model, CPU, or other hardware specifications used for running the experiments.
Software Dependencies No The paper does not specify any software dependencies with version numbers (e.g., Python 3.x, PyTorch 1.x, or specific libraries with versions).
Experiment Setup No The paper mentions 'Sec. C in the appendix provides detailed descriptions about the methods and the hyperparameter settings.' However, it does not provide these specific experimental setup details, hyperparameters, or system-level training settings within the main text.