Abstract:Relational learning is a challenging problem that has motivated a wide range of approaches, including graph-based models (e.g., graph neural networks, graph transformers), tabular methods (e.g., tabular foundation models), and sequence-based approaches (e.g., large language models), each with its own advantages and limitations. We propose RelAgent, an LLM-based autonomous data scientist for relational learning, which operates in two phases. In the search phase, an LLM agent uses database, validation, and evaluation workspace tools to construct SQL feature programs and select a predictive model. In the inference phase, the resulting program is executed without further LLM calls. The final predictor consists of SQL queries and a classical model, enabling fast, deterministic, and intrinsically interpretable predictions: features are human-readable queries, and predictions depend only on the resulting query-defined feature map, enabling scalable deployment using standard database systems.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.07840 [cs.LG] |
| (or arXiv:2605.07840v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.07840 arXiv-issued DOI via DataCite (pending registration) |
From: Xingyue Huang [view email]
[v1]
Fri, 8 May 2026 15:06:12 UTC (2,437 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。