LakeHopper: Cross Data Lakes Column Type Annotation through Model Adaptation

TL;DR

LakeHopper is a framework that adapts pre-trained language models for column type annotation across different data lakes, reducing the need for extensive new annotations through model interaction, data selection, and incremental fine-tuning.

Contribution

We introduce LakeHopper, a novel approach for transferring pre-trained models to new data lakes with minimal annotations, addressing knowledge gaps and optimizing fine-tuning.

Findings

Effective transfer of models across data lakes demonstrated

Reduces annotation effort in new data lake environments

Improves accuracy with incremental fine-tuning

Abstract

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.