Transferring Fairness under Distribution Shifts via Fair Consistency Regularization
Authors: Bang An, Zora Che, Mucong Ding, Furong Huang
NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments on synthetic and real datasets, including image and tabular data, demonstrate that our approach effectively transfers fairness and accuracy under various types of distribution shifts. |
| Researcher Affiliation | Academia | Bang An Department of Computer Science University of Maryland, College Park bangan@umd.edu Zora Che Department of Computer Science Boston University zche@bu.edu Mucong Ding Department of Computer Science University of Maryland, College Park mcding@umd.edu Furong Huang Department of Computer Science University of Maryland, College Park furongh@umd.edu |
| Pseudocode | No | The paper includes a training diagram (Figure 2) and describes the algorithm components, but it does not present a formal pseudocode block or algorithm steps labeled “Algorithm”. |
| Open Source Code | Yes | Code is available at https://github.com/umd-huang-lab/transfer-fairness. |
| Open Datasets | Yes | We use UTKFace [71] as the source data and Fair Face [30] as the target data. [...] The synthetic dataset is adapted from the 3dshapes dataset [31]. [...] We further evaluate our method on the New Adult dataset [19]. |
| Dataset Splits | Yes | 3. If you ran experiments... (b) Did you specify all the training details (e.g., data splits, hyperparameters, how they were chosen)? [Yes] see Section D. [...] We set CA as the source domain and all the other states as the target domain. |
| Hardware Specification | No | The paper's checklist states “Did you include the total amount of compute and the type of resources used (e.g., type of GPUs, internal cluster, or cloud provider)? [Yes] see Section D”. However, Section D is not provided in the given text, so specific hardware details are not available in the main paper. |
| Software Dependencies | No | The paper mentions using specific models like VGG16 and MLP but does not list specific software dependencies with version numbers (e.g., Python 3.x, PyTorch 1.x). |
| Experiment Setup | No | The paper’s checklist states “Did you specify all the training details (e.g., data splits, hyperparameters, how they were chosen)? [Yes] see Section D”. However, Section D is not provided in the given text, so specific experimental setup details like hyperparameter values are not available in the main paper. |