MontePrep: Monte-Carlo-Driven Automatic Data Preparation without Target Data Instances
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914050569404416 |
|---|---|
| author | Ge, Congcong Liu, Yachuan Tang, Yixuan Zhu, Yifan Tu, Yaofeng Gao, Yunjun |
| author_facet | Ge, Congcong Liu, Yachuan Tang, Yixuan Zhu, Yifan Tu, Yaofeng Gao, Yunjun |
| contents | In commercial systems, a pervasive requirement for automatic data preparation (ADP) is to transfer relational data from disparate sources to targets with standardized schema specifications. Previous methods rely on labor-intensive supervision signals or target table data access permissions, limiting their usage in real-world scenarios. To tackle these challenges, we propose an effective end-to-end ADP framework MontePrep, which enables training-free pipeline synthesis with zero target-instance requirements. MontePrep is formulated as an open-source large language model (LLM) powered tree-structured search problem. It consists of three pivot components, i.e., a data preparation action sandbox (DPAS), a fundamental pipeline generator (FPG), and an execution-aware pipeline optimizer (EPO). We first introduce DPAS, a lightweight action sandbox, to navigate the search-based pipeline generation. The design of DPAS circumvents exploration of infeasible pipelines. Then, we present FPG to build executable DP pipelines incrementally, which explores the predefined action sandbox by the LLM-powered Monte Carlo Tree Search. Furthermore, we propose EPO, which invokes pipeline execution results from sources to targets to evaluate the reliability of the generated pipelines in FPG. In this way, unreasonable pipelines are eliminated, thus facilitating the search process from both efficiency and effectiveness perspectives. Extensive experimental results demonstrate the superiority of MontePrep with significant improvement against five state-of-the-art competitors. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_17553 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MontePrep: Monte-Carlo-Driven Automatic Data Preparation without Target Data Instances Ge, Congcong Liu, Yachuan Tang, Yixuan Zhu, Yifan Tu, Yaofeng Gao, Yunjun Artificial Intelligence Databases Machine Learning In commercial systems, a pervasive requirement for automatic data preparation (ADP) is to transfer relational data from disparate sources to targets with standardized schema specifications. Previous methods rely on labor-intensive supervision signals or target table data access permissions, limiting their usage in real-world scenarios. To tackle these challenges, we propose an effective end-to-end ADP framework MontePrep, which enables training-free pipeline synthesis with zero target-instance requirements. MontePrep is formulated as an open-source large language model (LLM) powered tree-structured search problem. It consists of three pivot components, i.e., a data preparation action sandbox (DPAS), a fundamental pipeline generator (FPG), and an execution-aware pipeline optimizer (EPO). We first introduce DPAS, a lightweight action sandbox, to navigate the search-based pipeline generation. The design of DPAS circumvents exploration of infeasible pipelines. Then, we present FPG to build executable DP pipelines incrementally, which explores the predefined action sandbox by the LLM-powered Monte Carlo Tree Search. Furthermore, we propose EPO, which invokes pipeline execution results from sources to targets to evaluate the reliability of the generated pipelines in FPG. In this way, unreasonable pipelines are eliminated, thus facilitating the search process from both efficiency and effectiveness perspectives. Extensive experimental results demonstrate the superiority of MontePrep with significant improvement against five state-of-the-art competitors. |
| title | MontePrep: Monte-Carlo-Driven Automatic Data Preparation without Target Data Instances |
| topic | Artificial Intelligence Databases Machine Learning |
| url | https://arxiv.org/abs/2509.17553 |