MMM-fair: An Interactive Toolkit for Exploring and Operationalizing Multi-Fairness Trade-offs
This addresses the need for equitable AI by providing a comprehensive toolkit for exploring multi-dimensional fairness trade-offs, which is incremental as it builds on existing fairness-aware methods with enhanced features.
The authors tackled the problem of balancing performance and fairness in classification, particularly with intersectional biases and conflicting fairness definitions, by developing mmm-fair, an open-source toolkit that dynamically optimizes model weights to minimize errors and fairness violations, enabling flexible multi-objective optimization.
Fairness-aware classification requires balancing performance and fairness, often intensified by intersectional biases. Conflicting fairness definitions further complicate the task, making it difficult to identify universally fair solutions. Despite growing regulatory and societal demands for equitable AI, popular toolkits offer limited support for exploring multi-dimensional fairness and related trade-offs. To address this, we present mmm-fair, an open-source toolkit leveraging boosting-based ensemble approaches that dynamically optimizes model weights to jointly minimize classification errors and diverse fairness violations, enabling flexible multi-objective optimization. The system empowers users to deploy models that align with their context-specific needs while reliably uncovering intersectional biases often missed by state-of-the-art methods. In a nutshell, mmm-fair uniquely combines in-depth multi-attribute fairness, multi-objective optimization, a no-code, chat-based interface, LLM-powered explanations, interactive Pareto exploration for model selection, custom fairness constraint definition, and deployment-ready models in a single open-source toolkit, a combination rarely found in existing fairness tools. Demo walkthrough available at: https://youtu.be/_rcpjlXFqkw.