Inherent Tradeoffs in Learning Fair Representations
Authors: Han Zhao, Geoff Gordon
NeurIPS 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Finally, our theoretical findings are also confirmed empirically on real-world datasets. Empirically, we conduct experiments on a real-world dataset that corroborate both our positive and negative results. |
| Researcher Affiliation | Collaboration | Han Zhao Machine Learning Department School of Computer Science Carnegie Mellon University han.zhao@cs.cmu.edu Geoffrey J. Gordon Microsoft Research, Montreal Machine Learning Department Carnegie Mellon University geoff.gordon@microsoft.com |
| Pseudocode | No | The paper does not contain any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any explicit statements about releasing source code or links to a code repository for the methodology described. |
| Open Datasets | Yes | Dataset The Adult dataset contains 30,162/15,060 training/test instances for income prediction. Each instance in the dataset describes an adult from the 1994 US Census. |
| Dataset Splits | No | The paper states the dataset contains '30,162/15,060 training/test instances' but does not explicitly mention a validation split or provide details on how one might be derived. |
| Hardware Specification | No | The paper does not specify any particular hardware (e.g., GPU, CPU models, or cloud resources) used for running the experiments. |
| Software Dependencies | No | The paper mentions general software components like 'feed-forward network with ReLU activations' and 'logistic regression model' but does not provide specific version numbers for any libraries, frameworks, or programming languages used (e.g., Python, PyTorch, TensorFlow versions). |
| Experiment Setup | Yes | Experimental Protocol To validate the effect of learning group-invariant representations with adversarial debiasing techniques [5, 26, 34], we perform a controlled experiment by fixing the baseline network architecture to be a three hidden-layer feed-forward network with Re LU activations. The number of units in each hidden layer are 500, 200, and 100, respectively. The output layer corresponds to a logistic regression model. For debiasing with adversarial learning techniques, the adversarial discriminator network takes the feature from the last hidden layer as input, and connects it to a hidden-layer with 50 units, followed by a binary classifier whose goal is to predict the sensitive attribute A. To see how the adversarial loss affects the joint error, the demographic parity as well as the accuracy parity, we vary the coefficient ρ for the adversarial loss between 0.1, 1.0, 5.0 and 50.0. |