让表格模型自动公平预测，训练时就加约束。
Training Fair Tabular Foundation Models
- 用合成公平任务和梯度反转层，让模型学无关敏感属性的表示。
- 132个任务测试中，公平性显著提升，准确率仍保持竞争力。
- 适合需公平决策的金融、医疗等高风险场景使用。
表格基础模型（TFMs）已成为表格式预测任务的主流方法，利用上下文学习在无需特定任务训练的情况下对新数据进行预测。尽管TFMs在高风险决策中应用日益广泛，其公平性却未被充分研究。本文将公平性约束直接融入TFM训练过程，实现单次前向传播即可生成公平预测。针对训练数据中敏感属性获取受限及现有公平技术与上下文学习不兼容两大挑战，提出FairTFM：一种基于合成公平任务的可扩展训练策略，结合公平感知架构与梯度反转层，促使模型学习对敏感属性不变的表示。在132个公平性任务上的实验表明，该方法在保持竞争性准确率的同时，持续提升公平性表现。
原文摘要 · Abstract (English)
Tabular Foundation Models (TFMs) have emerged as leading methods for tabular predictive tasks, leveraging in-context learning to predict on new data without task-specific training. Despite the increased use of TFMs in high-stakes decision-making, their fairness properties remain largely unexplored. In this work, we incorporate fairness constraints directly into TFM training, enabling fair predictions in a single forward pass. Our approach addresses two key challenges: limited access to sensitive attributes in training data, and the incompatibility of existing fairness techniques with the in-context learning paradigm. We propose FairTFM, a scalable training strategy based on synthetic fairness tasks and a fairness-aware architecture using a gradient reversal layer, which encourages the model to learn representations invariant to sensitive attributes. Experiments on 132 fairness tasks show consistent improvements in fairness while maintaining competitive accuracy.
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。