Related papers: Mitra: Mixed Synthetic Priors for Enhancing Tabula…

Class-incremental learning (CIL) for time series data faces critical challenges in balancing stability against catastrophic forgetting and plasticity for new knowledge acquisition, particularly under real-world constraints where historical…

Transfer learning (TL) from pretrained deep models is a standard practice in modern medical image classification (MIC). However, what levels of features to be reused are problem-dependent, and uniformly finetuning all layers of pretrained…

Tabular data underpins decisions across science, industry, and public services. Despite rapid progress, advances in deep learning have not fully carried over to the tabular domain, where gradient-boosted decision trees (GBDTs) remain a…

Transformer-based tabular foundation models (TFMs) dominate small to medium tabular predictive benchmark tasks, yet their inference mechanisms remain largely unexplored. We present the first large-scale mechanistic study of layerwise…

Pre-training is prevalent in nowadays deep learning to improve the learned model's performance. However, in the literature on federated learning (FL), neural networks are mostly initialized with random weights. These attract our interest in…

Realistic synthetic tabular data generation encounters significant challenges in preserving privacy, especially when dealing with sensitive information in domains like finance and healthcare. In this paper, we introduce \textit{Federated…

Cross-frequency transfer learning (CFTL) has emerged as a popular framework for curating large-scale time series datasets to pre-train foundation forecasting models (FFMs). Although CFTL has shown promise, current benchmarking practices…

Recent text and image foundation models are incredibly impressive, and these models are attracting an ever-increasing portion of research resources. In this position piece we aim to shift the ML research community's priorities ever so…

The recently developed Prior-Data Fitted Networks (PFNs) have shown very promising results for applications in low-data regimes. The TabPFN model, a special case of PFNs for tabular data, is able to achieve state-of-the-art performance on a…

Federated Learning (FL) enables distributed machine learning training while preserving privacy, representing a paradigm shift for data-sensitive and decentralized environments. Despite its rapid advancements, FL remains a complex and…

Despite the commendable progress of recent LLM-based data synthesis methods, they face two limitations in generating table instruction tuning data. First, they can not thoroughly explore the vast input space of table understanding tasks,…

Industrial recommendation systems typically involve multiple scenarios, yet existing cross-domain (CDR) and multi-scenario (MSR) methods often require prohibitive resources and strict input alignment, limiting their extensibility. We…

Tabular data is prevalent in many critical domains, yet it is often challenging to acquire in large quantities. This scarcity usually results in poor performance of machine learning models on such data. Data augmentation, a common strategy…

Diffusion models have emerged as a robust framework for various generative tasks, including tabular data synthesis. However, current tabular diffusion models tend to inherit bias in the training dataset and generate biased synthetic data,…

Predictive modeling in engineering applications has long been dominated by bespoke models and small, siloed tabular datasets, limiting the applicability of large-scale learning approaches. Despite recent progress in tabular foundation…

Foundation models refer to deep learning models pretrained on large unlabeled datasets through self-supervised algorithms. In the Earth science and remote sensing communities, there is growing interest in transforming the use of Earth…

Informed machine learning methods allow the integration of prior knowledge into learning systems. This can increase accuracy and robustness or reduce data needs. However, existing methods often assume hard constraining knowledge, that does…

Tabular Foundation Models have recently established the state of the art in supervised tabular learning, by leveraging pretraining to learn generalizable representations of numerical and categorical structured data. However, they lack…

Synthetic tabular data are often evaluated by distributional similarity, privacy distance, or train-on-synthetic-test-on-real predictive performance, but these criteria do not ensure validity for causal inference. We show that fully…

Foundation models are transforming machine learning across many modalities, with in-context learning replacing classical model training. Recent work on tabular data hints at a similar opportunity to build foundation models for…