Notice: This website is continuously updated as new conference proceedings and journal volumes are published. Consequently, the figures presented here may differ from those reported in our publications.
A brief overview of our methodology is provided on the Methods page, along with references to publications documenting our approach and links to the code and data used in each study.
The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates.
Individual Fairness Revisited: Transferring Techniques from Adversarial Robustness
Authors: Samuel Yeom, Matt Fredrikson
IJCAI 2020 | Venue PDF | LLM Run Details | Input Tokens: 16,902 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 4,056 Total number of tokens produced by the LLM (including reasoning/thinking tokens) for this paper's analysis.
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Our experiments show that adapting the minimal metrics of linear models to more complicated neural networks can lead to meaningful and interpretable fairness guarantees at little cost to utility. Our results on four real datasets show that the neural networks smoothed with Gaussian noise in particular are often approximately as accurate as the original models. |
| Researcher Affiliation | Academia | Samuel Yeom and Matt Fredrikson Carnegie Mellon University EMAIL |
| Pseudocode | No | In the extended version of this paper [Yeom and Fredrikson, 2020], we provide pseudocode of an implementation of randomized smoothing. |
| Open Source Code | No | The paper refers to an extended version for pseudocode, but does not provide a specific link or explicit statement about the release of source code for the methodology within this paper. |
| Open Datasets | Yes | Our model uses the five numerical features from the UCI Adult dataset [Dua and Karra Taniskidou, 2017] to predict whether a person earns more than $50,000 per year. We use the dataset compiled by Pro Publica [Angwin et al., 2016] to analyze the COMPAS recidivism prediction model [Equivant, 2019]. The Strategic Subject List dataset [City of Chicago, 2017] contains scores given by Chicago Police Department s model... In the UCI Epileptic Seizure dataset [Dua and Karra Taniskidou, 2017; Andrzejak et al., 2001]... |
| Dataset Splits | No | The paper does not explicitly provide training/validation/test dataset splits with specific percentages or counts. It mentions training data augmentation and sampling for smoothing but not the overall data partitioning. |
| Hardware Specification | No | The paper mentions 'an NVIDIA GPU grant' in the acknowledgments but does not specify the exact model of the GPU or any other hardware components (CPU, memory, etc.) used for running the experiments. |
| Software Dependencies | No | The paper mentions using neural networks and logistic regression models but does not provide specific version numbers for any software dependencies or libraries. |
| Experiment Setup | Yes | For each dataset, we trained a neural network f with two dense hidden layers of 128 Re LU neurons each, as well as a logistic regression model to use for deriving the targeted metric. When training neural networks, we augmented training data with noise drawn from the smoothing distribution, as prior work [Cohen et al., 2019] shows that this improves the utility of the smoothed model. For smoothing, we sampled n = 105 points, which by Theorem 8 corresponds to a guarantee of δ = 1.8 10 4 at ϵ = 10 2. |