LaTable: Towards Large Tabular Models

• URL: http://arxiv.org/abs/2406.17673v1
• Date: Tue, 25 Jun 2024 16:03:50 GMT
• Title: LaTable: Towards Large Tabular Models
• Authors: Boris van Breugel, Jonathan Crabbé, Rob Davis, Mihaela van der Schaar,
• Abstract summary: 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.
• Score: 63.995130144110156
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Tabular data is one of the most ubiquitous modalities, yet the literature on tabular generative foundation models is lagging far behind its text and vision counterparts. Creating such a model is hard, due to the heterogeneous feature spaces of different tabular datasets, tabular metadata (e.g. dataset description and feature headers), and tables lacking prior knowledge (e.g. feature order). In this work we propose LaTable: a novel tabular diffusion model that addresses these challenges and can be trained across different datasets. Through extensive experiments we find that LaTable outperforms baselines on in-distribution generation, and that finetuning LaTable can generate out-of-distribution datasets better with fewer samples. On the other hand, we explore the poor zero-shot performance of LaTable, and what it may teach us about building generative tabular foundation models with better zero- and few-shot generation capabilities.

Related papers

• TabSketchFM: Sketch-based Tabular Representation Learning for Data Discovery over Data Lakes [25.169832192255956]
  We present TabFM, a neural tabular model for data discovery over data lakes. We finetune the pretrained model for identifying unionable, joinable, and subset table pairs. Our results demonstrate significant improvements in F1 scores for search compared to state-of-the-art techniques.
  arXiv  Detail & Related papers  (2024-06-28T17:28:53Z)
• Large Scale Transfer Learning for Tabular Data via Language Modeling [30.44823668480631]
  We present TabuLa-8B, a language model for tabular prediction. We show that TabuLa-8B has zero-shot accuracy on unseen tables that is over 15 percentage points (pp) higher than random guessing. We release our model, code, and data along with the publication of this paper.
  arXiv  Detail & Related papers  (2024-06-17T18:58:20Z)
• Training-Free Generalization on Heterogeneous Tabular Data via Meta-Representation [67.30538142519067]
  We propose Tabular data Pre-Training via Meta-representation (TabPTM) A deep neural network is then trained to associate these meta-representations with dataset-specific classification confidences. Experiments validate that TabPTM achieves promising performance in new datasets, even under few-shot scenarios.
  arXiv  Detail & Related papers  (2023-10-31T18:03:54Z)
• Privately generating tabular data using language models [80.67328256105891]
  Privately generating synthetic data from a table is an important brick of a privacy-first world. We propose and investigate a simple approach of treating each row in a table as a sentence and training a language model with differential privacy.
  arXiv  Detail & Related papers  (2023-06-07T21:53:14Z)
• QTSumm: Query-Focused Summarization over Tabular Data [58.62152746690958]
  People primarily consult tables to conduct data analysis or answer specific questions. We define a new query-focused table summarization task, where text generation models have to perform human-like reasoning. We introduce a new benchmark named QTSumm for this task, which contains 7,111 human-annotated query-summary pairs over 2,934 tables.
  arXiv  Detail & Related papers  (2023-05-23T17:43:51Z)
• Generative Table Pre-training Empowers Models for Tabular Prediction [71.76829961276032]
  We propose TapTap, the first attempt that leverages table pre-training to empower models for tabular prediction. TapTap can generate high-quality synthetic tables to support various applications, including privacy protection, low resource regime, missing value imputation, and imbalanced classification. It can be easily combined with various backbone models, including LightGBM, Multilayer Perceptron (MLP) and Transformer.
  arXiv  Detail & Related papers  (2023-05-16T06:37:38Z)
• Leveraging Data Recasting to Enhance Tabular Reasoning [21.970920861791015]
  Prior work has mostly relied on two data generation strategies. The first is human annotation, which yields linguistically diverse data but is difficult to scale. The second category for creation is synthetic generation, which is scalable and cost effective but lacks inventiveness.
  arXiv  Detail & Related papers  (2022-11-23T00:04:57Z)
• STable: Table Generation Framework for Encoder-Decoder Models [5.07112098978226]
  We propose a framework for text-to-table neural models applicable to problems such as extraction of line items, joint entity and relation extraction, or knowledge base population. The training maximizes the expected log-likelihood for a table's content across all random permutations of the factorization order. Experiments demonstrate a high practical value of the framework, which establishes state-of-the-art results on several challenging datasets.
  arXiv  Detail & Related papers  (2022-06-08T17:59:02Z)
• ToTTo: A Controlled Table-To-Text Generation Dataset [61.83159452483026]
  ToTTo is an open-domain English table-to-text dataset with over 120,000 training examples. We introduce a dataset construction process where annotators directly revise existing candidate sentences from Wikipedia. While usually fluent, existing methods often hallucinate phrases that are not supported by the table.
  arXiv  Detail & Related papers  (2020-04-29T17:53:45Z)

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.