Counterfactual refers to imagining alternate scenarios or outcomes that could have occurred if certain variables or attributes were different, especially concerning sensitive features like gender or race. For example, a counterfactual approach would examine how a model’s decision would change if an individual’s sensitive attributes (such as race or gender) were altered while keeping all other factors constant. The goal is to ensure that changes in sensitive attributes do not unfairly affect the outcome, helping to maintain fairness in model predictions. In the Disentanglement for Counterfactual Fairness-aware Domain Generalization (DCFDG) framework, counterfactual fairness is achieved by removing sensitive and domain-specific information from the feature representation so that model decisions are based only on relevant and fair attributes.

Posts

Towards Counterfactual Fairness-aware Domain Generalization in Changing Environments

/in /by

Recognizing domain generalization as a commonplace challenge in machine learning, data distribution might progressively evolve across a continuum of sequential domains in practical scenarios. While current methodologies primarily concentrate on bolstering model effectiveness within these new domains, they tend to neglect issues of fairness throughout the learning process. In response, we propose an innovative framework known as Disentanglement for Counterfactual Fairness-aware Domain Generalization (DCFDG). This approach adeptly removes domain-specific information and sensitive information from the embedded representation of classification features. To scrutinize the intricate interplay between semantic information, domain-specific information, and sensitive attributes, we systematically partition the exogenous factors into four latent variables. By incorporating fairness regularization, we utilize semantic information exclusively for classification purposes. Empirical validation on synthetic and authentic datasets substantiates the efficacy of our approach, demonstrating elevated accuracy levels while ensuring the preservation of fairness amidst the evolving landscape of continuous domains.

Read more