Relational databases (RDBs) contain vast amounts of heterogeneous tabular information that can be exploited for predictive modeling purposes. But since the space of potential targets is vast across enterprise settings, how can we avoid retraining a new model each time we wish to predict a new quantity of interest? Foundation models based on in-context learning (ICL) offer a convenient option, but so far are largely restricted to single-table operability. In generalizing to multiple interrelated tables, it is essential to compress variably-sized RDB neighborhoods into fixed-length ICL samples for consumption by the decoder. However, the details here are critical: unlike existing supervised learning RDB pipelines, we provide theoretical and empirical evidence that ICL-specific compression should be constrained within high-dimensional RDB columns where all entities share units and roles, not across columns where the relevance of heterogeneous data types cannot be determined without extensive label information. Conditioned on this restriction, we then demonstrate that encoder expressiveness is actually not compromised by excluding trainable parameters. Hence we arrive at a principled family of RDB encoders that can be seamlessly paired with already-existing single-table ICL foundation models, whereby no training or fine-tuning is required. From a practical standpoint, we develop scalable SQL primitives to implement the encoder stage, resulting in the easy-to-use open-source RDBLearn foundation model capable of robust performance on unseen datasets out of the box.

翻译：关系数据库（RDB）包含大量异构表格信息，可用于预测建模。但由于企业场景中潜在目标空间极为庞大，我们如何避免每次预测新目标时都重新训练模型？基于上下文学习（ICL）的基础模型提供了便捷方案，但至今主要局限于单表操作。在推广至多关联表时，需将可变大小的RDB邻域压缩为固定长度的ICL样本供解码器处理。然而细节至关重要：与传统监督学习RDB流水线不同，我们提供理论与实证证据表明，ICL特定压缩应限制在实体共享单位与角色的高维RDB列内，而非跨列压缩——因为无法在缺乏大量标签信息的情况下确定异构数据类型间的相关性。在此约束下，我们进一步证明排除可训练参数并不会削弱编码器表达能力。由此提出一组符合原则的RDB编码器，可与现有单表ICL基础模型无缝配对，且无需训练或微调。从实用角度出发，我们开发了可扩展的SQL原语来实现编码阶段，最终形成易用的开源RDBLearn基础模型，能够在未见数据集上开箱即用并保持稳健性能。