Related papers: Scaling TabPFN: Sketching and Feature Selection fo…

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…

A semi-supervised learning framework using the feedforward-designed convolutional neural networks (FF-CNNs) is proposed for image classification in this work. One unique property of FF-CNNs is that no backpropagation is used in model…

Contrastive learning is a model pre-training technique by first creating similar views of the original data, and then encouraging the data and its corresponding views to be close in the embedding space. Contrastive learning has witnessed…

In this work, we propose data augmentation methods for embeddings from pre-trained deep learning models that take a weighted combination of a pair of input embeddings, as inspired by Mixup, and combine such augmentation with extra label…

The use of patterns in predictive models is a topic that has received a lot of attention in recent years. Pattern mining can help to obtain models for structured domains, such as graphs and sequences, and has been proposed as a means to…

Tabular data is prevalent across diverse domains in machine learning. With the rapid progress of deep tabular prediction methods, especially pretrained (foundation) models, there is a growing need to evaluate these methods systematically…

Performance of a pre-trained semantic segmentation model is likely to substantially decrease on data from a new domain. We show a pre-trained model can be adapted to unlabelled target domain data by calculating soft-label prototypes under…

Transfer learning is a machine learning technique that uses previously acquired knowledge from a source domain to enhance learning in a target domain by reusing learned weights. This technique is ubiquitous because of its great advantages…

Anomaly detection in tabular data is challenging due to high dimensionality, complex feature dependencies, and heterogeneous noise. Many existing methods rely on proximity-based cues and may miss anomalies caused by violations of complex…

Tabular data is one of the most commonly used types of data in machine learning. Despite recent advances in neural nets (NNs) for tabular data, there is still an active discussion on whether or not NNs generally outperform gradient-boosted…

Foundation Models (FMs) have demonstrated remarkable insights into the relational dynamics of the world, leading to the crucial question: how do these models acquire an understanding of world hybrid relations? Traditional statistical…

Recently, graph neural networks (GNNs) have been shown powerful capacity at modeling structural data. However, when adapted to downstream tasks, it usually requires abundant task-specific labeled data, which can be extremely scarce in…

Scaling laws motivate the development of Time Series Foundation Models (TSFMs) that pre-train vast parameters and achieve remarkable zero-shot forecasting performance. Surprisingly, even after fine-tuning, TSFMs cannot consistently…

Computing the importance of features in supervised classification tasks is critical for model interpretability. Shapley values are a widely used approach for explaining model predictions, but require direct access to the underlying model,…

Deep Neural Networks (DNN) have shown great promise in many classification applications, yet are widely known to have poorly calibrated predictions when they are over-parametrized. Improving DNN calibration without comprising on model…

Large, pre-trained models are problematic to use in resource constrained applications. Fortunately, task-aware structured pruning methods offer a solution. These approaches reduce model size by dropping structural units like layers and…

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…

Tabular data underpins most high-value prediction problems in science and industry, and TabPFN has driven the foundation model revolution for this modality. Designed with feedback from our users, TabPFN-3 builds on this foundation to scale…

Recently, there has been an explosion in statistical learning literature to represent data using topological principles to capture structure and relationships. We propose a topological data analysis (TDA)-based framework, named Topological…

Data in tabular format is frequently occurring in real-world applications. Graph Neural Networks (GNNs) have recently been extended to effectively handle such data, allowing feature interactions to be captured through representation…