arXiv cs.AI· Hiren Madhu, Sukanta Ganguly, Kiran Srinivasan, Smita Krishnaswamy, Rex Ying·· 4 小时前AI 评分35
MoREGT:专家引导的关系专家混合图 Transformer 实现跨数据库泛化
Experts Across Schemas: Agent-Guided Mixture-of-Relational-Experts for Cross-Database Generalization
AI 导读
arXiv 论文提出 MoREGT,一种关系专家混合图 Transformer,将行和单元格表示为 token,并按列元数据而非取值路由到专家。在 21 个 RelBench 任务、六个数据库上留一数据库外预训练的设置下,其骨干比相同数据库预训练的 Relational Transformer 平均 AUROC 高 2.25 点、平均 nMAE 低 5.83 点。
正文 · 原文
Abstract:Web platforms record user and item activity in relational databases whose schemas differ from platform to platform, which makes it difficult to transfer predictive models between them. Relational foundation models address this through cross-database pretraining, yet recent improvements have relied on increasingly large pretraining corpora. We ask whether a better architecture, together with features specific to the target database, can deliver comparable gains from far less pretraining data. We introduce MoREGT, a mixture-of-relational-experts graph transformer that represents both rows and cells as tokens, adds the log-ages of rows and the names of foreign-key relationships to attention, and routes cells and rows to experts by column metadata rather than by values. A label-blind LLM agent complements the model: it reads the target database's schema and column statistics and adds validated single-row derived columns, without access to labels or model scores. On 21 RelBench tasks with leave-one-database-out pretraining on six databases, the MoREGT backbone improves on the Relational Transformer pretrained on the same databases by 2.25 points of mean AUROC and 5.83 points of mean nMAE. The agent's columns raise mean AUROC from 78.45 to 79.63 and lower mean nMAE from 27.91 to 26.98, the highest means on both metrics among the compared methods, including RT-J, which pretrains on about 400 times as many databases.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.18315 [cs.AI] |
| (or arXiv:2611.18315v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.18315 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Hiren Madhu [view email]
[v1]
Fri, 13 Nov 2026 15:32:09 UTC (500 KB)
来源:arXiv cs.AI · arxiv.org