Related papers: TabPFN: One Model to Rule Them All?
Training deep learning models and performing hyperparameter tuning can be computationally demanding and time-consuming. Meanwhile, traditional machine learning methods like gradient-boosting algorithms remain the preferred choice for most…
Conditional density estimation (CDE) - recovering the full conditional distribution of a response given tabular covariates - is essential in settings with heteroscedasticity, multimodality, or asymmetric uncertainty. Recent tabular…
We propose Tabular Q-Learning (TabQL), a reinforcement learning framework that replaces the conventional parametric Q-network in Deep Q-Learning (DQN) with a tabular foundation model endowed with in-context learning capabilities. The key…
Despite the prevalence and significance of tabular data across numerous industries and fields, it has been relatively underexplored in the realm of deep learning. Even today, neural networks are often overshadowed by techniques such as…
Data organized in tabular format is ubiquitous in real-world applications, and users often craft tables with biased feature definitions and flexibly set prediction targets of their interests. Thus, a rapid development of a robust,…
Missing data is a widespread problem in tabular settings. Existing solutions range from simple averaging to complex generative adversarial networks, but due to each method's large variance in performance across real-world domains and…
Transformers have shown impressive results in tabular data generation. However, they lack domain-specific inductive biases which are critical for preserving the intrinsic characteristics of tabular data. They also suffer from poor…
In the field of Explainable AI (XAI), counterfactual (CF) explanations are one prominent method to interpret a black-box model by suggesting changes to the input that would alter a prediction. In real-world applications, the input is…
Deep learning has achieved impressive performance in many domains, such as computer vision and natural language processing, but its advantage over classical shallow methods on tabular datasets remains questionable. It is especially…
Prior-data fitted networks (PFNs) have recently been proposed as a promising way to train tabular foundation models. PFNs are transformers that are pre-trained on synthetic data generated from a prespecified prior distribution and that…
With the growing popularity of deep learning and foundation models for tabular data, the need for standardized and reliable benchmarks is higher than ever. However, current benchmarks are static. Their design is not updated even if flaws…
In-context learners like TabPFN are promising for biomolecule efficacy prediction, where established molecular feature sets and relevant experimental results can serve as powerful contextual examples. However, their performance is highly…
Prior-data fitted networks (PFNs) have achieved exceptional performance on tabular classification tasks. However, like other classifiers, their performance can suffer under the effect of class imbalance, resulting in poor performance for…
In the field of pedometrics, tabular machine learning is the predominant method for soil property prediction from remote and proximal soil sensing data, forming a central component of Digital Soil Mapping (DSM). At the field-scale, this…
We present SHAPNN, a novel deep tabular data modeling architecture designed for supervised learning. Our approach leverages Shapley values, a well-established technique for explaining black-box models. Our neural network is trained using…
Deep generative models for engineering design often require substantial computational cost, large training datasets, and extensive retraining when design requirements or datasets change, limiting their applicability in real-world…
We present a deep transformation model for probabilistic regression. Deep learning is known for outstandingly accurate predictions on complex data but in regression tasks, it is predominantly used to just predict a single number. This…
Tabular data are central to many real-world systems. While recent tabular transformers and in-context learners such as SAINT, TP-BERTa, TabPFN, TabICL, and MITRA incorporate limited inter-row reasoning, most approaches still lack an…
Tabular foundation models aim to learn universal representations of tabular data that transfer across tasks and domains, enabling applications such as table retrieval, semantic search and table-based prediction. Despite the growing number…
Predictive modeling on tabular data is the cornerstone of many real-world applications. Although gradient boosting machines and some recent deep models achieve strong performance on tabular data, they often lack interpretability. On the…