用大模型当数据科学家，自动构建可解释的关联学习预测系统
RelAgent: LLM Agents as Data Scientists for Relational Learning
- 大模型自主生成SQL特征程序并选型经典模型
- 最终预测由可读SQL和传统模型构成，运行快速且结果确定
- 适合需要透明可解释性与数据库部署的工业场景
关联学习是一个具有挑战性的任务，已有多种方法，包括基于图的模型（如图神经网络、图Transformer）、表格方法（如表格基础模型）以及基于序列的方法（如大语言模型），各有优劣。我们提出RelAgent，一种基于大语言模型的自主数据科学家，用于关联学习，分为两个阶段：在搜索阶段，大模型代理利用数据库、验证和评估工作区工具，构建SQL特征程序并选择预测模型；在推理阶段，生成的程序无需进一步调用大模型即可执行。最终预测器由SQL查询和经典模型组成，实现快速、确定性和内在可解释的预测：特征为人类可读的查询，预测仅依赖于查询定义的特征映射，可使用标准数据库系统实现可扩展部署。
原文摘要 · Abstract (English)
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.
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。