Analysis

The generated report can be viewed in three different formats, where the model card contains a subset of results but attaches to these socio-technical concerns to be taken into account:

1. A summary table of results.
2. A simplified model card that includes concerns.
3. The full report, including details.

The module's report summarizes how a model behaves on a provided dataset across different population groups. These groups are based on sensitive attributes like gender, age, and race. Each attribute can have multiple values, such as several genders or races. Numeric attributes, like age, are normalized to the range [0,1] and treated as fuzzy values, where 0 indicates membership to a fuzzy group of "small" values, and 1 indicates membership to a fuzzy group of "large" values. A separate set of fairness metrics is calculated for each prediction label.

If intersectional subgroup analysis is enabled, separate subgroups are created for each combination of sensitive attribute values. However, if there are too many attributes, some groups will be small or empty. Empty groups are ignored in the analysis.

The assessment is conducted over sensitive attributes like gender, age, and race. Each attribute can have multiple values, such as several genders or races. Numeric attributes, like age, are normalized to the range [0,1] and treated as fuzzy values, where 0 indicates membership to a fuzzy group of "small" values, and 1 indicates membership to a fuzzy group of "large" values. A separate set of fairness metrics is calculated for each prediction label.

If intersectional subgroup analysis is enabled, separate subgroups are created for each combination of sensitive attribute values. However, if there are too many attributes, some groups will be small or empty. Empty groups are ignored in the analysis.

If strong biases appear in the simple models that are explored, they may also persist in more complex models trained on the same data. To focus on the most significant biases, adjust the minimum shown deviation parameter. The report provides multiple types of fairness and bias assessments and can be viewed in three different formats, where the model card contains a subset of results but attaches to these socio-technical concerns to be taken into account:

1. A summary table of results.
2. A simplified model card with key fairness concerns.
3. A full detailed report.

The module's report summarizes how a model behaves on a provided dataset across different population groups. These groups are based on sensitive attributes like gender, age, and race. Each attribute can have multiple values, such as several genders or races. Numeric attributes, like age, are normalized to the range [0,1] and treated as fuzzy values, where 0 indicates membership to a fuzzy group of "small" values, and 1 indicates membership to a fuzzy group of "large" values. A separate set of fairness metrics is calculated for each prediction label.

If intersectional subgroup analysis is enabled, separate subgroups are created for each combination of sensitive attribute values. However, if there are too many attributes, some groups will be small or empty. Empty groups are ignored in the analysis. The report may also include information about built-in datasets.

If strong biases appear in the simple models that are explored, they may also persist in more complex models trained on the same data. To focus on the most significant biases, adjust the minimum shown deviation parameter. The report provides multiple types of fairness and bias assessments and can be viewed in three different formats, where the model card contains a subset of results but attaches to these socio-technical concerns to be taken into account:

1. A summary table of results.
2. A simplified model card with key fairness concerns.
3. A full detailed report.

The module's report summarizes how a model behaves on a provided dataset across different population groups. These groups are based on sensitive attributes like gender, age, and race. Each attribute can have multiple values, such as several genders or races. Numeric attributes, like age, are normalized to the range [0,1] and treated as fuzzy values, where 0 indicates membership to a fuzzy group of "small" values, and 1 indicates membership to a fuzzy group of "large" values. A separate set of fairness metrics is calculated for each prediction label.

If intersectional subgroup analysis is enabled, separate subgroups are created for each combination of sensitive attribute values. However, if there are too many attributes, some groups will be small or empty. Empty groups are ignored in the analysis. The report may also include information about built-in datasets.

Creates an optimal transport evaluation based on the implementation provided by the AIF360 library. The evaluation computes the Wasserstein distance that reflects the cost of transforming the predictive distributions between sensitive attribute groups.

Optimal Transport (OT) is a field of mathematics which studies the geometry of probability spaces. Among its many contributions, OT provides a principled way to compare and align probability distributions by taking into account the underlying geometry of the considered metric space. As a mathematical problem, it was first introduced by Gaspard Monge in 1781. It addresses the task of determining the most efficient method for transporting mass from one distribution to another. In this problem, the cost associated with moving a unit of mass from one position to another is referred to as the ground cost. The primary objective of OT is to minimize the total cost incurred when moving one mass distribution onto another.

OT can be used to detect model-induced bias by calculating the a cost known as Earth Mover's distance or Wasserstein distance between the distribution of ground truth labels and model predictions for each of the protected groups. If its value is close to 1, the model is biased towards this group.

License

Parts of the above description are adapted from AIF360 (https://github.com/Trusted-AI/AIF360), which is licensed under Apache License 2.0.

A paper describing how this approach estimates biased intersection candidates in linear rather than exponential time is available here. Instead of checking every possible combination (which can be very time-consuming), it uses a more efficient method.

For convenience, there is a discovery mode available in the parameters. This automatically adds attributes suspected of contributing to bias to the list of ignored (already known sensitive) ones, then reruns the scan. While this automation helps streamline the process, it removes all attributes contributing to biased intersections. A domain expert may prefer to manually remove one attribute at a time by adding it to known sensitive attributes and rerun the module to investigate more granular effects on the results.

Rather than explaining each individual image separately, FaceX aggregates information across the entire dataset, offering a broader view of the model's behavior. It looks at how the model activates different regions of the face for each decision. This aggregated information helps you see which facial features are most influential in the model's predictions, and whether certain features are being emphasized more than others.

In addition to providing an overall picture of which regions are important, FaceX also zooms in on specific areas of the face - such as a section of the skin or a part of the hair - showing which patches of the image have the highest impact on the model's decision. This makes it easier to identify potential biases or problems in how the model is interpreting the face.

Overall, with FaceX, you can quickly and easily get a better understanding of your model's decision-making process. This is especially useful for ensuring that your model is fair and transparent, and for spotting any potential biases that may affect its performance.

The key idea is that FaceX analyzes the facial regions in the image that most influence how the model compares the reference embedding with the new image's embedding. Rather than providing an explanation for individual images in isolation, FaceX aggregates information across the dataset, offering insights into how different parts of the face, such as the eyes, mouth, or hair, contribute to the similarity or difference between the reference and the image being compared.

FaceX works by using a "reference" image (e.g., identity image) and evaluating how other images (e.g., selfies) compare to it. It looks at how various facial regions of the new image align with the reference image in the feature space. The tool then highlights which facial regions are most influential in the comparison, showing what aspects of the image are similar to or different from the concept embedding.

Overall, FaceX gives you a better understanding of how the model processes and compares facial features by highlighting the specific regions that influence the similarity or difference in feature embeddings. This is especially useful for improving transparency and identifying potential biases in how face verification models represent and compare faces.

Two sets of visual outputs are processed:

• Group-wise metrics: Shown as grouped bar charts, these display performance metrics (e.g., false positive rate) across subgroups.
• Scalar metrics: Displayed as horizontal bar charts, these summarize disparities (e.g., equal opportunity difference) in a compact, interpretable format.

Interactive charts allow users to hover for precise values, compare metrics between groups, and quickly identify fairness gaps. An explanation panel is included to define each metric and guide interpretation. This module is well suited for exploratory analysis, presentations, and fairness monitoring. It makes group disparities visible and intuitive, helping identify where further scrutiny or mitigation may be needed.

Two types of fairness metrics are considered:

• Group-wise metrics: These show how the model performs for each group separately (e.g., true positive rates for Group A vs. Group B).
• Scalar metrics: These summarize disparities across groups into single numeric values. Small differences and ratios close to 1 indicate balanced treatment.

Results are presented in aligned tables with clear formatting, allowing users to compare outcomes across groups at a glance. Each metric is briefly explained to help interpret whether the model exhibits performance or outcome disparities for different groups. This module is particularly useful in evaluation pipelines, audit reports, and model reviews where transparency and fairness are essential. It helps teams assess group-level equity in model behavior using interpretable, tabular summaries.

• Class: Balances the class distribution within each subgroup by sampling the minority class.
• Class & Protected: Ensures equal sample distribution across all subgroups by sampling both majority

and minority classes.

• Protected: Balances the number of instances across different groups without considering class labels.
• Class (Ratio): Maintains the same class ratio across all groups as found in the largest group.

These visualizations allow users to observe the effects of each strategy on the data distribution, helping to understand how the dataset is being augmented.

For more information, refer to our full paper: "Synthetic Tabular Data Generation for Class Imbalance and Fairness: A Comparative Study" Link to paper.

This report provides is generated by MAI-BIAS to generate an overview of dataset imbalances across the intersection of sensitive attributes and prediction targets using the MMM-Fair library. Intersectionality emphasizes that people experience overlapping systems of discrimination based on multiple identity characteristics (race, gender, class, sexual orientation, disability, etc.). This is reflected also in how AI systems reproduce forms of discrimination. As an example of intersectional bias [1] race and gender together affect algorithmic performance of commercial facial-analysis systems; worst performance for darker-skinned women demonstrates a compounded disparity that would be missed if the analysis looked only at race or only at gender.

[1] Buolamwini, J., & Gebru, T. (2018, January). Gender shades: Intersectional accuracy disparities in commercial gender classification. In Conference on fairness, accountability and transparency (pp. 77-91). PMLR.

Imbalanced datasets can lead to biased model behavior, as underrepresented subgroups are more difficult to predict correctly. Intersections of many sensitive attributes (e.g., low-income hispanic woman) may create tiny or empty groups. Augmentation strategies increase the representation of such subgroups, which can improve fairness and robustness of downstream models.