一站式公平性工具，支持多维度公平权衡与交互式模型选择。
MMM-fair: An Interactive Toolkit for Exploring and Operationalizing Multi-Fairness Trade-offs
- 基于提升集成方法动态优化权重，同时降低分类误差与多种公平性违规。
- 可交互探索帕累托前沿，识别被主流方法忽略的交叉偏见。
- 无需编码的聊天界面+大模型解释，适合非技术用户快速部署公平模型。
公平感知分类需在性能与公平性间权衡，常受交叉性偏见加剧。不同公平定义间的冲突使寻找普适公平解更加困难。尽管对公平AI的需求日益增长，现有工具对多维公平性及其权衡的支持有限。为此，我们提出 mmm-fair，一个开源工具包，采用基于提升的集成方法，动态优化模型权重以联合最小化分类误差与多样公平性违规，支持灵活的多目标优化。该系统使用户可根据上下文需求部署模型，并可靠发现主流方法常遗漏的交叉性偏见。简言之，mmm-fair 首次将深度多属性公平性分析、多目标优化、无代码聊天界面、大模型驱动解释、交互式帕累托探索、自定义公平约束定义及部署就绪模型整合于单一开源工具中，这一组合在现有公平性工具中罕见。演示视频：https://youtu.be/_rcpjlXFqkw。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。