发表机构
ÉTS Montréal; Mila - Quebec AI Institute; Layer 6 AI; University of Calgary; CIFAR（蒙特利尔高等技术学院; 米拉-魁北克人工智能研究所; 第六层人工智能公司; 卡尔加里大学; 加拿大高级研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对表格基础模型（TFMs）公平性未被充分探索的问题，本研究提出FairTFM训练策略，将公平约束融入TFMs训练，在132个公平任务上实现公平性提升且保持竞争力准确性。
AI 中文摘要
表格基础模型（Tabular Foundation Models, TFMs）已成为表格预测任务的领先方法，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增多，但其公平性特性仍未得到充分探索。本研究将公平约束直接融入TFMs的训练，使模型能在单次前向传播中生成公平预测。我们的方法解决了两个关键挑战：训练数据中敏感属性的获取受限，以及现有公平技术与上下文学习范式不兼容。我们提出了FairTFM，一种基于合成公平任务和使用梯度反转层的公平感知架构的可扩展训练策略，该策略鼓励模型学习对敏感属性不变的表示。在132个公平任务上的实验表明，我们的方法在保持竞争力准确性的同时，公平性得到了持续提升。
英文摘要
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.
CommentsSpotlight paper at the ICML 2026 Workshop on Foundation Models for Structured Data
