LakeHopper: Cross Data Lakes Column Type Annotation through Model Adaptation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915786555129856 |
|---|---|
| author | Sun, Yushi Li, Xujia Tang, Nan Xu, Quanqing Yang, Chuanhui Chen, Lei |
| author_facet | Sun, Yushi Li, Xujia Tang, Nan Xu, Quanqing Yang, Chuanhui Chen, Lei |
| contents | Column type annotation is vital for tasks like data cleaning, integration, and visualization. Recent solutions rely on resource-intensive language models fine-tuned on well-annotated columns from a particular set of tables, i.e., a source data lake. In this paper, we study whether we can adapt an existing pre-trained LM-based model to a new (i.e., target) data lake to minimize the annotations required on the new data lake. However, challenges include the source-target knowledge gap, selecting informative target data, and fine-tuning without losing shared knowledge exist. We propose LakeHopper, a framework that identifies and resolves the knowledge gap through LM interactions, employs a cluster-based data selection scheme for unannotated columns, and uses an incremental fine-tuning mechanism that gradually adapts the source model to the target data lake. Our experimental results validate the effectiveness of LakeHopper on two different data lake transfers under both low-resource and high-resource settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_08793 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | LakeHopper: Cross Data Lakes Column Type Annotation through Model Adaptation Sun, Yushi Li, Xujia Tang, Nan Xu, Quanqing Yang, Chuanhui Chen, Lei Computation and Language Databases Column type annotation is vital for tasks like data cleaning, integration, and visualization. Recent solutions rely on resource-intensive language models fine-tuned on well-annotated columns from a particular set of tables, i.e., a source data lake. In this paper, we study whether we can adapt an existing pre-trained LM-based model to a new (i.e., target) data lake to minimize the annotations required on the new data lake. However, challenges include the source-target knowledge gap, selecting informative target data, and fine-tuning without losing shared knowledge exist. We propose LakeHopper, a framework that identifies and resolves the knowledge gap through LM interactions, employs a cluster-based data selection scheme for unannotated columns, and uses an incremental fine-tuning mechanism that gradually adapts the source model to the target data lake. Our experimental results validate the effectiveness of LakeHopper on two different data lake transfers under both low-resource and high-resource settings. |
| title | LakeHopper: Cross Data Lakes Column Type Annotation through Model Adaptation |
| topic | Computation and Language Databases |
| url | https://arxiv.org/abs/2602.08793 |