通过可迁移表征实现文本分类公平性，避免依赖敏感属性
Fair Text Classification via Transferable Representations
- 用Wasserstein依赖度量促使标签与敏感属性表征解耦
- 在无需敏感属性数据下，仍能有效降低群体偏差
- 结合领域自适应，适用于真实场景中的公平分类
群体公平是文本分类的核心研究议题，实现敏感群体（如女性与男性）间公平对待仍是开放挑战。本文提出一种方法，扩展使用Wasserstein依赖度量来学习无偏见的神经文本分类器。针对文本编码器中难以区分公平与不公平信息的问题，受对抗训练启发，我们促使目标标签与敏感属性所学表征相互独立。进一步表明，可通过领域自适应有效消除对数据集中敏感属性的依赖。本文提供理论与实证证据，证明该方法具有坚实基础。
原文摘要 · Abstract (English)
Group fairness is a central research topic in text classification, where reaching fair treatment between sensitive groups (e.g., women and men) remains an open challenge. We propose an approach that extends the use of the Wasserstein Dependency Measure for learning unbiased neural text classifiers. Given the challenge of distinguishing fair from unfair information in a text encoder, we draw inspiration from adversarial training by inducing independence between representations learned for the target label and those for a sensitive attribute. We further show that Domain Adaptation can be efficiently leveraged to remove the need for access to the sensitive attributes in the dataset we cure. We provide both theoretical and empirical evidence that our approach is well-founded.
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。