TabSketchFM: Sketch-based Tabular Representation Learning for Data Discovery over Data Lakes

TL;DR

TabSketchFM introduces a neural model with sketch-based pre-training for effective data discovery in data lakes, significantly improving table search accuracy and generalization across datasets.

Contribution

The paper presents a novel sketch-based pre-training method for neural tabular models, enhancing data discovery tasks like identifying unionable, joinable, and subset tables.

Findings

Significant F1 score improvements over state-of-the-art methods.

Effective transferability across datasets and tasks.

Detailed ablation study on sketch importance.

Abstract

Enterprises have a growing need to identify relevant tables in data lakes; e.g. tables that are unionable, joinable, or subsets of each other. Tabular neural models can be helpful for such data discovery tasks. In this paper, we present TabSketchFM, a neural tabular model for data discovery over data lakes. First, we propose novel pre-training: a sketch-based approach to enhance the effectiveness of data discovery in neural tabular models. Second, we finetune the pretrained model for identifying unionable, joinable, and subset table pairs and show significant improvement over previous tabular neural models. Third, we present a detailed ablation study to highlight which sketches are crucial for which tasks. Fourth, we use these finetuned models to perform table search; i.e., given a query table, find other tables in a corpus that are unionable, joinable, or that are subsets of the query. Our results demonstrate significant improvements in F1 scores for search compared to state-of-the-art techniques. Finally, we show significant transfer across datasets and tasks establishing that our model can generalize across different tasks and over different data lakes.