TabPFN is a Prior-Data Fitted Network that approximates Bayesian inference for small tabular classification by training a Transformer once on synthetic data drawn from a causal prior, then solves new tasks in a single forward pass without further updates.
hub
SAINT: Improved neural networks for tabular data via row attention and contrastive pre-training.arXiv preprint arXiv:2106.01342
15 Pith papers cite this work. Polarity classification is still indexing.
15
Pith papers citing it
hub tools
representative citing papers
TabPFN-MT is a multitask in-context learner for tabular data that sets a new state-of-the-art on deep multitask learning for datasets under 1000 samples while reducing inference cost from O(T) to O(1) passes.
RelPrism generates self-supervised pseudo-tasks from three attribute perspectives via multi-granularity clustering to improve representation learning for relational database prediction tasks.
SAGA applies a decoder-only transformer with split conformal prediction to multi-horizon labor earnings forecasting on Swedish panel data, outperforming parametric baselines with guaranteed coverage intervals.
WISE unifies representation via BEP, feature weighting via LOFO, two-stage clustering, and intrinsic explanations via DFI for mixed-type tabular data, outperforming baselines on six datasets.
Spline encodings for numerical features show task-dependent performance in tabular deep learning, with piecewise-linear encoding robust for classification and variable results for regression depending on spline family, knot strategy, and backbone.
Tabular VAEs show ~50% lower causal circuit modularity than image VAEs, with beta-VAE CES collapsing to 0.043 versus 0.133 due to reconstruction degradation, challenging direct transfer of image interpretability techniques.
FEAT is a linear-complexity structured data foundation model using dual-axis encoding, AFBM state-space models, and Conv-GLA to achieve O(N) scaling and permutation invariance while outperforming prior SFMs on real-world benchmarks.
MultiModalPFN extends TabPFN with modality projectors, a multi-head gated MLP, and cross-attention pooler to unify tabular and non-tabular inputs, outperforming prior methods on medical and general multimodal datasets.
Tabular foundation models outperform standard methods in credit risk PD and LGD tasks, with larger gains on smaller datasets when used out-of-the-box.
A BART-GraphSAGE hybrid achieves ROC-AUC 67.40 on one RelBench task, competitive with LightGBM but still behind specialized relational deep learning and foundation models.
PRAGMA pre-trains a Transformer on heterogeneous banking events with a tailored self-supervised masked objective, yielding embeddings that support strong downstream performance on credit scoring, fraud detection, and lifetime value prediction using linear heads or light fine-tuning.
Benchmarks TabPFN, MambaNet and MambaAttention on imbalanced EV crash severity classification with SMOTEENN resampling on Texas data, identifying intersection relation and speed limit as top features and MambaAttention as strongest on severe cases.
Standalone tree-based models outperform both SAINT and SAINT-embedding hybrids for employee attrition prediction on tabular HR data.
citing papers explorer
-
TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second
TabPFN is a Prior-Data Fitted Network that approximates Bayesian inference for small tabular classification by training a Transformer once on synthetic data drawn from a causal prior, then solves new tasks in a single forward pass without further updates.
-
TabPFN-MT: A Natively Multitask In-Context Learner for Tabular Data
TabPFN-MT is a multitask in-context learner for tabular data that sets a new state-of-the-art on deep multitask learning for datasets under 1000 samples while reducing inference cost from O(T) to O(1) passes.
-
RelPrism: A Multi-Faceted Pre-training Framework with Self-Generated Tasks for Relational Databases
RelPrism generates self-supervised pseudo-tasks from three attribute perspectives via multi-granularity clustering to improve representation learning for relational database prediction tasks.
-
SAGA: A Sequence-Adaptive Generative Architecture for Multi-Horizon Probabilistic Forecasting with Adaptive Temporal Conformal Prediction
SAGA applies a decoder-only transformer with split conformal prediction to multi-horizon labor earnings forecasting on Swedish panel data, outperforming parametric baselines with guaranteed coverage intervals.
-
Weight-Informed Self-Explaining Clustering for Mixed-Type Tabular Data
WISE unifies representation via BEP, feature weighting via LOFO, two-stage clustering, and intrinsic explanations via DFI for mixed-type tabular data, outperforming baselines on six datasets.
-
From Uniform to Learned Knots: A Study of Spline-Based Numerical Encodings for Tabular Deep Learning
Spline encodings for numerical features show task-dependent performance in tabular deep learning, with piecewise-linear encoding robust for classification and variable results for regression depending on spline family, knot strategy, and backbone.
-
Posterior-Calibrated Causal Circuits in Variational Autoencoders: Why Image-Domain Interpretability Fails on Tabular Data
Tabular VAEs show ~50% lower causal circuit modularity than image VAEs, with beta-VAE CES collapsing to 0.043 versus 0.133 due to reconstruction degradation, challenging direct transfer of image interpretability techniques.
-
FEAT: A Linear-Complexity Foundation Model for Extremely Large Structured Data
FEAT is a linear-complexity structured data foundation model using dual-axis encoding, AFBM state-space models, and Conv-GLA to achieve O(N) scaling and permutation invariance while outperforming prior SFMs on real-world benchmarks.
-
MultiModalPFN: Extending Prior-Data Fitted Networks for Multimodal Tabular Learning
MultiModalPFN extends TabPFN with modality projectors, a multi-head gated MLP, and cross-attention pooler to unify tabular and non-tabular inputs, outperforming prior methods on medical and general multimodal datasets.
-
Foundation Models for Credit Risk Prediction: A Game Changer?
Tabular foundation models outperform standard methods in credit risk PD and LGD tasks, with larger gains on smaller datasets when used out-of-the-box.
-
Towards Foundation Models for Relational Databases with Language Models and Graph Neural Networks
A BART-GraphSAGE hybrid achieves ROC-AUC 67.40 on one RelBench task, competitive with LightGBM but still behind specialized relational deep learning and foundation models.
-
PRAGMA: Revolut Foundation Model
PRAGMA pre-trains a Transformer on heterogeneous banking events with a tailored self-supervised masked objective, yielding embeddings that support strong downstream performance on credit scoring, fraud detection, and lifetime value prediction using linear heads or light fine-tuning.
-
Tabular Data with Class Imbalance: Predicting Electric Vehicle Crash Severity with Pretrained Transformers (TabPFN) and Mamba-Based Models
Benchmarks TabPFN, MambaNet and MambaAttention on imbalanced EV crash severity classification with SMOTEENN resampling on Texas data, identifying intersection relation and speed limit as top features and MambaAttention as strongest on severe cases.
-
Integrating SAINT with Tree-Based Models: A Case Study in Employee Attrition Prediction
Standalone tree-based models outperform both SAINT and SAINT-embedding hybrids for employee attrition prediction on tabular HR data.
- Mitigating Label Shift in Tabular In-Context Learning via Test-Time Posterior Adjustment