提出可处理任意目标维度的表格模型，提升预测稳定性与效率。
EquiTabPFN: A Target-Permutation Equivariant Prior Fitted Networks
- 设计全目标等变架构，通过等变编码器和注意力机制实现排列不变性
- 在类别数超过预训练范围的数据集上表现优于现有方法，计算开销更低
- 适合需要灵活处理多标签任务的工业场景，如金融风控、医疗诊断
近期基于表格数据的基础模型（如 TabPFN）可通过上下文学习快速适应新任务，但受限于固定的目标维度数量，常需昂贵的集成策略。我们发现其根本缺陷在于缺乏目标等变性：目标维度顺序的置换会改变预测结果，导致不可消除的“等变性差距”，引发预测不稳定性。为此，我们设计了全目标等变的 EquiTabPFN 架构，通过等变编码器、解码器及双向注意力机制实现排列不变性。在标准分类基准上的实证表明，在类别数超过预训练时所见数量的数据集上，该模型表现匹配或超越现有方法，且计算开销更低。
原文摘要 · Abstract (English)
Recent foundational models for tabular data, such as TabPFN, excel at adapting to new tasks via in-context learning, but remain constrained to a fixed, pre-defined number of target dimensions-often necessitating costly ensembling strategies. We trace this constraint to a deeper architectural shortcoming: these models lack target equivariance, so that permuting target dimension orderings alters their predictions. This deficiency gives rise to an irreducible "equivariance gap", an error term that introduces instability in predictions. We eliminate this gap by designing a fully target-equivariant architecture-ensuring permutation invariance via equivariant encoders, decoders, and a bi-attention mechanism. Empirical evaluation on standard classification benchmarks shows that, on datasets with more classes than those seen during pre-training, our model matches or surpasses existing methods while incurring lower computational overhead.
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。