Towards Evaluating Data Priors for Tabular Foundation Models

• URL: http://arxiv.org/abs/2606.29241v1
• Date: Sun, 28 Jun 2026 07:12:45 GMT
• Title: Towards Evaluating Data Priors for Tabular Foundation Models
• Abstract summary: We implement a unified interface for publicly available priors and priors constructed from real datasets.<n>We generate training tasks from each prior, train the same model architecture under a fixed training protocol, and evaluate the resulting models on shared downstream classification tasks.<n>Our results show that different priors favor different downstream behaviors, with some achieving stronger absolute performance and others exhibiting more consistent relative rankings across datasets.
• Score: 74.75794086564035
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Data-generating priors are a central component of tabular foundation models because they define the task distribution used during pretraining. However, priors are rarely evaluated as independent components, making it difficult to understand how much they affect downstream model behavior. This raises a methodological question: how can priors from different tabular foundation models be compared independently of the architectures and training protocols they were introduced with? To study this question, we implement a unified interface for publicly available priors from recent tabular foundation models and priors constructed from real datasets. We generate training tasks from each prior, train the same model architecture under a fixed training protocol, and evaluate the resulting models on shared downstream classification tasks. We compare priors through both generated-task statistics and downstream predictive performance. Our results show that different priors favor different downstream behaviors, with some achieving stronger absolute performance and others exhibiting more consistent relative rankings across datasets. We further find that data-level similarity only partially explains downstream behavior. Our code is available at https://github.com/automl/TFM-Playground/tree/prior-dev.

Related papers

• Mitra: Mixed Synthetic Priors for Enhancing Tabular Foundation Models [85.64873567417396]
  We introduce Mitra, a TFM trained on a curated mixture of synthetic priors selected for their diversity, distinctiveness, and performance on real-world data.<n>Mitra consistently outperforms state-of-the-art TFMs, such as TabPFNv2 and TabICL, across both classification and regression benchmarks.
  arXiv  Detail & Related papers  (2025-10-24T07:15:06Z)
• Estimating Time Series Foundation Model Transferability via In-Context Learning [74.65355820906355]
  Time series foundation models (TSFMs) offer strong zero-shot forecasting via large-scale pre-training.<n>Fine-tuning remains critical for boosting performance in domains with limited public data.<n>We introduce TimeTic, a transferability estimation framework that recasts model selection as an in-context-learning problem.
  arXiv  Detail & Related papers  (2025-09-28T07:07:13Z)
• Zero-shot Meta-learning for Tabular Prediction Tasks with Adversarially Pre-trained Transformer [2.1677183904102257]
  We present an Adversarially Pre-trained Transformer (APT) that is able to perform zero-shot meta-learning on tabular prediction tasks without pre-training on any real-world dataset.<n>APT is pre-trained with adversarial synthetic data agents, who deliberately challenge the model with different synthetic datasets.<n>We show that our framework matches state-of-the-art performance on small classification tasks without filtering on dataset characteristics.
  arXiv  Detail & Related papers  (2025-02-06T23:58:11Z)
• Analyzing Similarity Metrics for Data Selection for Language Model Pretraining [39.02299450717135]
  Measuring similarity between training examples is critical for curating high-quality and diverse pretraining datasets for language models.<n>Standard off-the-shelf embedding models are not well-suited for the pretraining data curation setting.
  arXiv  Detail & Related papers  (2025-02-04T17:09:44Z)
• Towards Better Understanding Table Instruction Tuning: Decoupling the Effects from Data versus Models [62.47618742274461]
  We fine-tune base models from the Mistral, OLMo, and Phi families on existing public training datasets.<n>Our replication achieves performance on par with or surpassing existing table LLMs.<n>We decouple the contributions of training data and the base model, providing insight into their individual impacts.
  arXiv  Detail & Related papers  (2025-01-24T18:50:26Z)
• Measuring Pre-training Data Quality without Labels for Time Series Foundation Models [10.64362760848387]
  We introduce contrastive accuracy, a new measure to evaluate the quality of the representation space learned by the foundation model.<n>Our experiments reveal the positive correlation between the proposed measure and the accuracy of the model on a collection of downstream tasks.
  arXiv  Detail & Related papers  (2024-12-09T10:38:30Z)
• Scaling TabPFN: Sketching and Feature Selection for Tabular Prior-Data Fitted Networks [31.82225213006849]
  Tabular classification has traditionally relied on supervised algorithms, which estimate the parameters of a prediction model using its training data. Recently, Prior-Data Fitted Networks (PFNs) such as TabPFN have successfully learned to classify tabular data in-context. While such models show great promise, their applicability to real-world data remains limited due to the computational scale needed.
  arXiv  Detail & Related papers  (2023-11-17T16:04:27Z)
• Never Train from Scratch: Fair Comparison of Long-Sequence Models Requires Data-Driven Priors [44.5740422079]
  We show that pretraining with standard denoising objectives leads to dramatic gains across multiple architectures. In stark contrast to prior works, we find vanilla Transformers to match the performance of S4 on Long Range Arena when properly pretrained.
  arXiv  Detail & Related papers  (2023-10-04T17:17:06Z)
• On the Transferability of Pre-trained Language Models: A Study from Artificial Datasets [74.11825654535895]
  Pre-training language models (LMs) on large-scale unlabeled text data makes the model much easier to achieve exceptional downstream performance. We study what specific traits in the pre-training data, other than the semantics, make a pre-trained LM superior to their counterparts trained from scratch on downstream tasks.
  arXiv  Detail & Related papers  (2021-09-08T10:39:57Z)
• Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning [36.047444794544425]
  We introduce a general-purpose deep learning architecture that takes as input the entire dataset instead of processing one datapoint at a time. Our approach uses self-attention to reason about relationships between datapoints explicitly. Unlike conventional non-parametric models, we let the model learn end-to-end from the data how to make use of other datapoints for prediction.
  arXiv  Detail & Related papers  (2021-06-04T16:30:49Z)
• Document Ranking with a Pretrained Sequence-to-Sequence Model [56.44269917346376]
  We show how a sequence-to-sequence model can be trained to generate relevance labels as "target words" Our approach significantly outperforms an encoder-only model in a data-poor regime.
  arXiv  Detail & Related papers  (2020-03-14T22:29:50Z)

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.