Related papers: Real-TabPFN: Improving Tabular Foundation Models v…

Federated Learning (FL) has lately gained traction as it addresses how machine learning models train on distributed datasets. FL was designed for parametric models, namely Deep Neural Networks (DNNs).Thus, it has shown promise on image and…

Foundation models compress a large amount of information in a single, large neural network, which can then be queried for individual tasks. There are strong parallels between this widespread framework and offline goal-conditioned…

For most natural language processing tasks, the dominant practice is to finetune large pretrained transformer models (e.g., BERT) using smaller downstream datasets. Despite the success of this approach, it remains unclear to what extent…

Tabular biomedical data is often high-dimensional but with a very small number of samples. Although recent work showed that well-regularised simple neural networks could outperform more sophisticated architectures on tabular data, they are…

Following its success for vision and text, the "foundation model" (FM) paradigm -- pretraining large models on massive data, then fine-tuning on target tasks -- has rapidly expanded to domains in the sciences, engineering, healthcare, and…

Transformer-based models have shown promising performance on tabular data compared to their classical counterparts such as neural networks and Gradient Boosted Decision Trees (GBDTs) in scenarios with limited training data. They utilize…

Table pretrain-then-finetune paradigm has been proposed and employed at a rapid pace after the success of pre-training in the natural language domain. Despite the promising findings in tabular pre-trained language models (TPLMs), there is…

Prior-data fitted networks (PFNs) have emerged as promising foundation models for prediction from tabular datasets, achieving state-of-the-art performance on small to moderate data sizes without tuning. While PFNs are motivated by Bayesian…

Large language models are commonly trained on a mixture of filtered web data and curated high-quality corpora, such as social media conversations, books, or technical papers. This curation process is believed to be necessary to produce…

Foundation models, pre-trained on massive datasets, have achieved unprecedented generalizability. However, is it truly necessary to involve such vast amounts of data in pre-training, consuming extensive computational resources? This paper…

Tabular data is ubiquitous in real-world applications and abundant on the web, yet its annotation has traditionally required human labor, posing a significant scalability bottleneck for tabular machine learning. Our methodology can…

Real-world model deployments demand strong performance on narrow domains where data is often scarce. Typically, practitioners finetune models to specialize them, but this risks overfitting to the domain and forgetting general knowledge. We…

Representation learning stands as one of the critical machine learning techniques across various domains. Through the acquisition of high-quality features, pre-trained embeddings significantly reduce input space redundancy, benefiting…

Tabular data (or tables) are the most widely used data format in machine learning (ML). However, ML models often assume the table structure keeps fixed in training and testing. Before ML modeling, heavy data cleaning is required to merge…

Tabular data is the most abundant data type in the world, powering systems in finance, healthcare, e-commerce, and beyond. As tabular datasets grow and span multiple related targets, there is an increasing need to exploit shared task…

Recent benchmarks found In-Context Learning (ICL) outperforms both deep learning and tree-based algorithms on small tabular datasets. However, on larger datasets, ICL for tabular learning cannot run without severely compromising…

We introduce KumoRFM-2, the next iteration of a pre-trained foundation model for relational data. KumoRFM-2 supports in-context learning as well as fine-tuning and is applicable to a wide range of predictive tasks. In contrast to tabular…

Large language models (LLMs) are increasingly exposed to data contamination, i.e., performance gains driven by prior exposure of test datasets rather than generalization. However, in the context of tabular data, this problem is largely…

Recent advances in foundation models have emphasized the need to align pre-trained models with specialized domains using small, curated datasets. Studies on these foundation models underscore the importance of low-data training and…

Existing work on tabular representation learning jointly models tables and associated text using self-supervised objective functions derived from pretrained language models such as BERT. While this joint pretraining improves tasks involving…