TabDPT: Scaling Tabular Foundation Models on Real Data

• URL: http://arxiv.org/abs/2410.18164v2
• Date: Sat, 12 Jul 2025 18:07:37 GMT
• Title: TabDPT: Scaling Tabular Foundation Models on Real Data
• Authors: Junwei Ma, Valentin Thomas, Rasa Hosseinzadeh, Hamidreza Kamkari, Alex Labach, Jesse C. Cresswell, Keyvan Golestan, Guangwei Yu, Anthony L. Caterini, Maksims Volkovs,
• Abstract summary: We propose an approach to combine ICL-based retrieval with self supervised learning to train foundation models.<n>We show that incorporating real data during the pre-training phase can lead to significantly faster training and better generalization to unseen data.<n>Our resulting model, TabDPT, achieves top performance on both regression (CTR23) and classification (CC18) benchmarks.
• Score: 20.00390825519329
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Tabular data is one of the most ubiquitous sources of information worldwide, spanning a wide variety of domains. This inherent heterogeneity has slowed the development of Tabular Foundation Models (TFMs) capable of fast generalization to unseen datasets. In-Context Learning (ICL) has recently emerged as a promising solution for TFMs, enabling dynamic adaptation to new tasks without additional tuning. While many studies have attempted to re-purpose large language models for tabular ICL, they have had limited success, so recent works have focused on developing tabular-specific foundation models. In this work, we propose an approach to combine ICL-based retrieval with self supervised learning to train tabular foundation models. We also investigate the utility of real vs. synthetic data for model pre-training, and show that real data can contain useful signal not easily captured in synthetic training. Specifically, we show that incorporating real data during the pre-training phase can lead to significantly faster training and better downstream generalization to unseen data. Our resulting model, TabDPT, achieves top performance on both regression (CTR23) and classification (CC18) benchmarks. Importantly, we also demonstrate that with our pre-training procedure, scaling both model and data size leads to consistent performance improvements that follow power laws. This echoes scaling laws in LLMs and other foundation models, and suggests that Internet-scale TFMs can be achievable. We open-source our full pipeline: inference code including trained model weights can be found at github.com/layer6ai-labs/TabDPT-inference, and the training code to reproduce experiments can be found at github.com/layer6ai-labs/TabDPT-training.

Related papers

• SPaRFT: Self-Paced Reinforcement Fine-Tuning for Large Language Models [51.74498855100541]
  Large language models (LLMs) have shown strong reasoning capabilities when fine-tuned with reinforcement learning (RL)<n>We propose textbfSPaRFT, a self-paced learning framework that enables efficient learning based on the capability of the model being trained.
  arXiv  Detail & Related papers  (2025-08-07T03:50:48Z)
• Real-TabPFN: Improving Tabular Foundation Models via Continued Pre-training With Real-World Data [38.08600450054975]
  We show that this performance can be significantly boosted by a targeted continued pre-training phase.<n>We demonstrate that leveraging a small, curated collection of large, real-world datasets for continued pre-training yields superior predictive downstream accuracy.<n>Our resulting model, Real-TabPFN, achieves substantial performance gains on 29 datasets from the OpenML AutoML Benchmark.
  arXiv  Detail & Related papers  (2025-07-05T09:39:07Z)
• Intention-Conditioned Flow Occupancy Models [69.79049994662591]
  Large-scale pre-training has fundamentally changed how machine learning research is done today.<n>Applying this same framework to reinforcement learning is appealing because it offers compelling avenues for addressing core challenges in RL.<n>Recent advances in generative AI have provided new tools for modeling highly complex distributions.
  arXiv  Detail & Related papers  (2025-06-10T15:27:46Z)
• TabPFN: One Model to Rule Them All? [21.658323618943697]
  We provide a tailored explanation of how TabPFN works for a statistics audience.<n>We show that an out-of-the-box application of TabPFN vastly outperforms specialized state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-05-26T13:55:29Z)
• Can Test-Time Scaling Improve World Foundation Model? [67.82670175383761]
  We introduce SWIFT, a test-time scaling framework tailored for world foundation models (WFMs)<n> Empirical results on the COSMOS model demonstrate that test-time scaling exists even in a compute-optimal way.<n>Our findings reveal that test-time scaling laws hold for WFMs and that SWIFT provides a scalable and effective pathway for improving WFM inference without retraining or increasing model size.
  arXiv  Detail & Related papers  (2025-03-31T17:07:37Z)
• Prior-Fitted Networks Scale to Larger Datasets When Treated as Weak Learners [82.72552644267724]
  BoostPFN can outperform standard PFNs with the same size of training samples in large datasets. High performance is maintained for up to 50x of the pre-training size of PFNs.
  arXiv  Detail & Related papers  (2025-03-03T07:31:40Z)
• A Closer Look at TabPFN v2: Strength, Limitation, and Extension [51.08999772842298]
  Tabular Prior-data Fitted Network v2 (TabPFN v2) achieves unprecedented in-context learning accuracy across multiple datasets. In this paper, we evaluate TabPFN v2 on over 300 datasets, confirming its exceptional generalization capabilities on small- to medium-scale tasks.
  arXiv  Detail & Related papers  (2025-02-24T17:38:42Z)
• TabICL: A Tabular Foundation Model for In-Context Learning on Large Data [15.08819125687632]
  We introduce TabICL, a foundation model for classification pretrained on synthetic datasets with up to 60K samples. It is on par with TabPFNv2 while being systematically faster (up to 10 times) and significantly outperforms all other approaches. On 56 datasets with over 10K samples, TabICL surpasses both TabPFNv2 and CatBoost, demonstrating the potential of ICL for large data.
  arXiv  Detail & Related papers  (2025-02-08T13:25:04Z)
• A Survey on Deep Tabular Learning [0.0]
  Tabular data presents unique challenges for deep learning due to its heterogeneous nature and lack of spatial structure. This survey reviews the evolution of deep learning models for Tabular data, from early fully connected networks (FCNs) to advanced architectures like TabNet, SAINT, TabTranSELU, and MambaNet.
  arXiv  Detail & Related papers  (2024-10-15T20:08:08Z)
• Accelerating Large Language Model Pretraining via LFR Pedagogy: Learn, Focus, and Review [50.78587571704713]
  Learn-Focus-Review (LFR) is a dynamic training approach that adapts to the model's learning progress. LFR tracks the model's learning performance across data blocks (sequences of tokens) and prioritizes revisiting challenging regions of the dataset. Compared to baseline models trained on the full datasets, LFR consistently achieved lower perplexity and higher accuracy.
  arXiv  Detail & Related papers  (2024-09-10T00:59:18Z)
• Unsupervised Pre-training with Language-Vision Prompts for Low-Data Instance Segmentation [105.23631749213729]
  We propose a novel method for unsupervised pre-training in low-data regimes. Inspired by the recently successful prompting technique, we introduce a new method, Unsupervised Pre-training with Language-Vision Prompts. We show that our method can converge faster and perform better than CNN-based models in low-data regimes.
  arXiv  Detail & Related papers  (2024-05-22T06:48:43Z)
• Unleashing the Potential of Large Language Models for Predictive Tabular Tasks in Data Science [17.910306140400046]
  This research endeavors to apply Large Language Models (LLMs) towards addressing these predictive tasks. Our research aims to mitigate this gap by compiling a comprehensive corpus of tables annotated with instructions and executing large-scale training of Llama-2.
  arXiv  Detail & Related papers  (2024-03-29T14:41:21Z)
• Diffusion-Based Neural Network Weights Generation [80.89706112736353]
  D2NWG is a diffusion-based neural network weights generation technique that efficiently produces high-performing weights for transfer learning. Our method extends generative hyper-representation learning to recast the latent diffusion paradigm for neural network weights generation. Our approach is scalable to large architectures such as large language models (LLMs), overcoming the limitations of current parameter generation techniques.
  arXiv  Detail & Related papers  (2024-02-28T08:34:23Z)
• In-Context Data Distillation with TabPFN [11.553950697974825]
  In-context data distillation (ICD) is a novel methodology that effectively eliminates these constraints by optimizing TabPFN's context. ICD efficiently enables TabPFN to handle significantly larger datasets with a fixed memory budget, improving TabPFN's quadratic memory complexity but at the cost of a linear number of tuning steps.
  arXiv  Detail & Related papers  (2024-02-10T15:23:45Z)
• Efficient Grammatical Error Correction Via Multi-Task Training and Optimized Training Schedule [55.08778142798106]
  We propose auxiliary tasks that exploit the alignment between the original and corrected sentences. We formulate each task as a sequence-to-sequence problem and perform multi-task training. We find that the order of datasets used for training and even individual instances within a dataset may have important effects on the final performance.
  arXiv  Detail & Related papers  (2023-11-20T14:50:12Z)
• 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)
• From Supervised to Generative: A Novel Paradigm for Tabular Deep Learning with Large Language Models [18.219485459836285]
  Generative Tabular Learning (GTL) is a novel framework that integrates the advanced functionalities of large language models (LLMs) Our empirical study spans 384 public datasets, rigorously analyzing GTL's scaling behaviors. GTL-LLaMA-2 model demonstrates superior zero-shot and in-context learning capabilities across numerous classification and regression tasks.
  arXiv  Detail & Related papers  (2023-10-11T09:37:38Z)
• The Languini Kitchen: Enabling Language Modelling Research at Different Scales of Compute [66.84421705029624]
  We introduce an experimental protocol that enables model comparisons based on equivalent compute, measured in accelerator hours. We pre-process an existing large, diverse, and high-quality dataset of books that surpasses existing academic benchmarks in quality, diversity, and document length. This work also provides two baseline models: a feed-forward model derived from the GPT-2 architecture and a recurrent model in the form of a novel LSTM with ten-fold throughput.
  arXiv  Detail & Related papers  (2023-09-20T10:31:17Z)
• Towards Cross-Table Masked Pretraining for Web Data Mining [22.952238405240188]
  We propose an innovative, generic, and efficient cross-table pretraining framework, dubbed as CM2. Our experiments demonstrate CM2's state-of-the-art performance and validate that cross-table pretraining can enhance various downstream tasks.
  arXiv  Detail & Related papers  (2023-07-10T02:27:38Z)
• Universal Domain Adaptation from Foundation Models: A Baseline Study [58.51162198585434]
  We make empirical studies of state-of-the-art UniDA methods using foundation models. We introduce textitCLIP distillation, a parameter-free method specifically designed to distill target knowledge from CLIP models. Although simple, our method outperforms previous approaches in most benchmark tasks.
  arXiv  Detail & Related papers  (2023-05-18T16:28:29Z)
• 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)
• INGENIOUS: Using Informative Data Subsets for Efficient Pre-Training of Language Models [40.54353850357839]
  We show how we can employ submodular optimization to select highly representative subsets of the training corpora. We show that the resulting models achieve up to $sim99%$ of the performance of the fully-trained models.
  arXiv  Detail & Related papers  (2023-05-11T09:24:41Z)
• PTab: Using the Pre-trained Language Model for Modeling Tabular Data [5.791972449406902]
  Recent studies show that neural-based models are effective in learning contextual representation for Tabular data. We propose a novel framework PTab, using the Pre-trained language model to model Tabular data. Our method has achieved a better average AUC score in supervised settings compared to the state-of-the-art baselines.
  arXiv  Detail & Related papers  (2022-09-15T08:58:42Z)

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.