解决关系学习中任务稀缺导致的标签泄露问题，提升模型迁移能力。
Task Scarcity and Label Leakage in Relational Transfer Learning
- 用冻结编码器+轻量消息传递核心的K-Space架构研究任务迁移
- 引入梯度投影法去除表示更新中的标签相关方向，平均提升0.145 AUROC
- 适合关注跨任务迁移与模型泛化性的研究人员
训练关系基础模型需学习可跨任务迁移的表示，但每个数据库通常仅有少量预测目标，造成任务稀缺。这导致学习到的表示会捕捉任务特异性捷径，即使在同一模式内也损害迁移性能，我们称此为标签泄露。本文使用K-Space——一种结合冻结预训练表格编码器与轻量级消息传递核心的模块化架构进行研究。为抑制泄露，提出一种梯度投影方法，从表示更新中移除标签预测方向。在RelBench上，该方法使同数据集内的迁移性能平均提升0.145 AUROC，常能恢复接近单任务水平的表现。结果表明，任务多样性不足，而不仅是数据量有限，是制约关系基础模型的关键因素。
原文摘要 · Abstract (English)
Training relational foundation models requires learning representations that transfer across tasks, yet available supervision is typically limited to a small number of prediction targets per database. This task scarcity causes learned representations to encode task-specific shortcuts that degrade transfer even within the same schema, a problem we call label leakage. We study this using K-Space, a modular architecture combining frozen pretrained tabular encoders with a lightweight message-passing core. To suppress leakage, we introduce a gradient projection method that removes label-predictive directions from representation updates. On RelBench, this improves within-dataset transfer by +0.145 AUROC on average, often recovering near single-task performance. Our results suggest that limited task diversity, not just limited data, constrains relational foundation models.
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。