Related papers: GEM-T: Generative Tabular Data via Fitting Moments

This study addresses the challenge of detecting semantic column types in relational tables, a key task in many real-world applications. While language models like BERT have improved prediction accuracy, their token input constraints limit…

Advances in deep generative modelling have not translated well to tabular data. We argue that this is caused by a mismatch in structure between popular generative models and discriminative models of tabular data. We thus devise a technique…

Generative models for tabular data have evolved rapidly beyond Generative Adversarial Networks (GANs). While GANs pioneered synthetic tabular data generation, recent advances in diffusion models and large language models (LLMs) have opened…

We present GEM, a Generalizable Ego-vision Multimodal world model that predicts future frames using a reference frame, sparse features, human poses, and ego-trajectories. Hence, our model has precise control over object dynamics, ego-agent…

Imbalanced datasets pose a difficulty in fraud detection, as classifiers are often biased toward the majority class and perform poorly on rare fraudulent transactions. Synthetic data generation is therefore commonly used to mitigate this…

While synthetic tabular data generation using Deep Generative Models (DGMs) offers a compelling solution to data scarcity and privacy concerns, their effectiveness relies on the availability of substantial training data, often lacking in…

As point cloud provides a natural and flexible representation usable in myriad applications (e.g., robotics and self-driving cars), the ability to synthesize point clouds for analysis becomes crucial. Recently, Xie et al. propose a…

We introduce a novel model called GAMMT (Generative Ambiguity Models using Multiple Transformers) for sequential data that is based on sets of probabilities. Unlike conventional models, our approach acknowledges that the data generation…

Generative models for network time series (also known as dynamic graphs) have tremendous potential in fields such as epidemiology, biology and economics, where complex graph-based dynamics are core objects of study. Designing flexible and…

Synthetic data is often positioned as a solution to replace sensitive fixed-size datasets with a source of unlimited matching data, freed from privacy concerns. There has been much progress in synthetic data generation over the last decade,…

We present our Generative Enhanced Model (GEM) that we used to create samples awarded the first prize on the FEVER 2.0 Breakers Task. GEM is the extended language model developed upon GPT-2 architecture. The addition of novel target…

Synthetic data generation becomes prevalent as a solution to privacy leakage and data shortage. Generative models are designed to generate a realistic synthetic dataset, which can precisely express the data distribution for the real…

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…

The data landscape is rich with structured data, often of high value to organizations, driving important applications in data analysis and machine learning. Recent progress in representation learning and generative models for such data has…

Synthetic tabular data generation has gained significant attention for its potential in data augmentation and privacy-preserving data sharing. While recent methods like diffusion and auto-regressive models (i.e., transformer) have advanced…

The growing demand for scalable psychological counseling highlights the need for high-quality, privacy-compliant data, yet such data remains scarce. Here we introduce MAGneT, a novel multi-agent framework for synthetic psychological…

Beyond their origin in modeling many-body quantum systems, tensor networks have emerged as a promising class of models for solving machine learning problems, notably in unsupervised generative learning. While possessing many desirable…

Electromyography (EMG)-based gesture recognition has emerged as a promising approach for human-computer interaction. However, its performance is often limited by the scarcity of labeled EMG data, significant cross-user variability, and poor…

A generative model based on training deep architectures is proposed. The model consists of K networks that are trained together to learn the underlying distribution of a given data set. The process starts with dividing the input data into K…

Handling imbalanced target distributions in regression poses a persistent challenge, as the underrepresentation of relevant target values can significantly hinder model performance. Existing data-level solutions often adapt…