TabSketchFM: Sketch-based Tabular Representation Learning for Data Discovery over Data Lakes
- URL: http://arxiv.org/abs/2407.01619v1
- Date: Fri, 28 Jun 2024 17:28:53 GMT
- Title: TabSketchFM: Sketch-based Tabular Representation Learning for Data Discovery over Data Lakes
- Authors: Aamod Khatiwada, Harsha Kokel, Ibrahim Abdelaziz, Subhajit Chaudhury, Julian Dolby, Oktie Hassanzadeh, Zhenhan Huang, Tejaswini Pedapati, Horst Samulowitz, Kavitha Srinivas,
- Abstract summary: We present TabSketchFM, a neural tabular model for data discovery over data lakes.
We propose a novel pre-training sketch-based approach to enhance the effectiveness of data discovery techniques.
We show improvements in F1 scores for search compared to state-of-the-art techniques.
- Score: 25.169832192255956
- License: http://creativecommons.org/licenses/by/4.0/
- 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 a novel pre-training sketch-based approach to enhance the effectiveness of data discovery techniques in neural tabular models. Second, to further finetune the pretrained model for several downstream tasks, we develop LakeBench, a collection of 8 benchmarks to help with different data discovery tasks such as finding tasks that are unionable, joinable, or subsets of each other. We then show on these finetuning tasks that TabSketchFM achieves state-of-the art performance compared to existing neural models. Third, we use these finetuned models to search for tables that are unionable, joinable, or can be subsets of each other. Our results demonstrate improvements in F1 scores for search compared to state-of-the-art techniques (even up to 70% improvement in a joinable search benchmark). Finally, we show significant transfer across datasets and tasks establishing that our model can generalize across different tasks over different data lakes
Related papers
- LaTable: Towards Large Tabular Models [63.995130144110156]
Tabular generative foundation models are hard to build due to the heterogeneous feature spaces of different datasets.
LaTable is a novel diffusion model that addresses these challenges and can be trained across different datasets.
We find that LaTable outperforms baselines on in-distribution generation, and that finetuning LaTable can generate out-of-distribution datasets better with fewer samples.
arXiv Detail & Related papers (2024-06-25T16:03:50Z) - Retrieve, Merge, Predict: Augmenting Tables with Data Lakes [7.449868392714658]
We analyze alternative methods used in the three main steps: retrieving joinable tables, merging information, and predicting with the resultant table.
As data lakes, the paper uses YADL (Yet Another Data Lake) and Open Data US, a well-referenced real data lake.
arXiv Detail & Related papers (2024-02-09T09:48:38Z) - Relational Deep Learning: Graph Representation Learning on Relational
Databases [69.7008152388055]
We introduce an end-to-end representation approach to learn on data laid out across multiple tables.
Message Passing Graph Neural Networks can then automatically learn across the graph to extract representations that leverage all data input.
arXiv Detail & Related papers (2023-12-07T18:51:41Z) - Relational Extraction on Wikipedia Tables using Convolutional and Memory
Networks [6.200672130699805]
Relation extraction (RE) is the task of extracting relations between entities in text.
We introduce a new model consisting of Convolutional Neural Network (CNN) and Bidirectional-Long Short Term Memory (BiLSTM) network to encode entities.
arXiv Detail & Related papers (2023-07-11T22:36:47Z) - Data-Efficient Finetuning Using Cross-Task Nearest Neighbors [75.07773863013001]
We use unlabeled target-task examples to retrieve most similar labeled examples from a pool of multitask data augmented with prompts.
Our approach of finetuning models on cross-task nearest neighbors is significantly more data-efficient.
arXiv Detail & Related papers (2022-12-01T00:53:04Z) - Why do tree-based models still outperform deep learning on tabular data? [0.0]
We show that tree-based models remain state-of-the-art on medium-sized data.
We conduct an empirical investigation into the differing inductive biases of tree-based models and Neural Networks (NNs)
arXiv Detail & Related papers (2022-07-18T08:36:08Z) - TabGNN: Multiplex Graph Neural Network for Tabular Data Prediction [43.35301059378836]
We propose a novel framework TabGNN based on recently popular graph neural networks (GNN)
Specifically, we firstly construct a multiplex graph to model the multifaceted sample relations, and then design a multiplex graph neural network to learn enhanced representation for each sample.
Experiments on eleven TDP datasets from various domains, including classification and regression ones, show that TabGNN can consistently improve the performance.
arXiv Detail & Related papers (2021-08-20T11:51:32Z) - When Can Models Learn From Explanations? A Formal Framework for
Understanding the Roles of Explanation Data [84.87772675171412]
We study the circumstances under which explanations of individual data points can improve modeling performance.
We make use of three existing datasets with explanations: e-SNLI, TACRED, SemEval.
arXiv Detail & Related papers (2021-02-03T18:57:08Z) - NASE: Learning Knowledge Graph Embedding for Link Prediction via Neural
Architecture Search [9.634626241415916]
Link prediction is the task of predicting missing connections between entities in the knowledge graph (KG)
Previous work has tried to use Automated Machine Learning (AutoML) to search for the best model for a given dataset.
We propose a novel Neural Architecture Search (NAS) framework for the link prediction task.
arXiv Detail & Related papers (2020-08-18T03:34:09Z) - Relation-Guided Representation Learning [53.60351496449232]
We propose a new representation learning method that explicitly models and leverages sample relations.
Our framework well preserves the relations between samples.
By seeking to embed samples into subspace, we show that our method can address the large-scale and out-of-sample problem.
arXiv Detail & Related papers (2020-07-11T10:57:45Z) - DeGAN : Data-Enriching GAN for Retrieving Representative Samples from a
Trained Classifier [58.979104709647295]
We bridge the gap between the abundance of available data and lack of relevant data, for the future learning tasks of a trained network.
We use the available data, that may be an imbalanced subset of the original training dataset, or a related domain dataset, to retrieve representative samples.
We demonstrate that data from a related domain can be leveraged to achieve state-of-the-art performance.
arXiv Detail & Related papers (2019-12-27T02:05:45Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.