首次研究联邦基础模型中多敏感属性的公平性因果关系。
Towards Group Fairness with Multiple Sensitive Attributes in Federated Foundation Models
- 构建可同时权衡多个敏感属性的联邦基础模型框架。
- 通过因果发现与推断量化不同属性间的公平性影响。
- 适用于医疗等需高公平性的敏感领域系统设计。
基础模型（FM）与联邦学习（FL）的深度融合提升了多样下游任务的个性化与可扩展性，在医疗等敏感领域尤为重要。在联邦基础模型（FFM）时代，群体公平性问题日益突出，因敏感属性中的偏差可能导致少数群体受到不公正对待。现有研究大多仅关注单一敏感属性的公平性，难以揭示多属性间的依赖关系，无法实现真正的群体公平。本文首次对联邦基础模型中多个敏感属性间群体公平性的因果关系进行分析，扩展了FFM结构以同时权衡多个敏感属性，并通过因果发现与推断量化其背后的影响机制。大量实验证明该方法有效，为构建可信赖、公平的FFM系统提供了可解释性支持。
原文摘要 · Abstract (English)
The deep integration of foundation models (FM) with federated learning (FL) enhances personalization and scalability for diverse downstream tasks, making it crucial in sensitive domains like healthcare. Achieving group fairness has become an increasingly prominent issue in the era of federated foundation models (FFMs), since biases in sensitive attributes might lead to inequitable treatment for under-represented demographic groups. Existing studies mostly focus on achieving fairness with respect to a single sensitive attribute. This renders them unable to provide clear interpretability of dependencies among multiple sensitive attributes which is required to achieve group fairness. Our paper takes the first attempt towards a causal analysis of the relationship between group fairness across various sensitive attributes in the FFM. We extend the FFM structure to trade off multiple sensitive attributes simultaneously and quantify the causal effect behind the group fairness through causal discovery and inference. Extensive experiments validate its effectiveness, offering insights into interpretability towards building trustworthy and fair FFM systems.
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。