Related papers: Engineering Regression Without Real-Data Training:…
Fully connected deep neural networks (DNN) often include redundant weights leading to overfitting and high memory requirements. Additionally, the performance of DNN is often challenged by traditional machine learning models in tabular data…
Instrumenting and collecting annotated visual grasping datasets to train modern machine learning algorithms can be extremely time-consuming and expensive. An appealing alternative is to use off-the-shelf simulators to render synthetic data…
Electronic Health Records have become popular sources of data for secondary research, but their use is hampered by the amount of effort it takes to overcome the sparsity, irregularity, and noise that they contain. Modern learning…
Transferring knowledge across different datasets is an important approach to successfully train deep models with a small-scale target dataset or when few labeled instances are available. In this paper, we aim at developing a model that can…
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…
Supervised learning with tabular data presents unique challenges, including low data sizes, the absence of structural cues, and heterogeneous features spanning both categorical and continuous domains. Unlike vision and language tasks, where…
Recent advances in deep learning have driven rapid progress in time series forecasting, yet many state-of-the-art models continue to struggle with robust performance in real-world applications, even when they achieve strong results on…
It is common to observe performance degradation when transferring models trained on some (source) datasets to target testing data due to a domain gap between them. Existing methods for bridging this gap, such as domain adaptation (DA), may…
As the demand for high-quality data in model training grows, researchers and developers are increasingly generating synthetic data to tune and train LLMs. However, current data generation methods rely on seed sets containing tens of…
The advent of artificial intelligence has significantly enhanced credit scoring technologies. Despite the remarkable efficacy of advanced deep learning models, mainstream adoption continues to favor tree-structured models due to their…
Many Transformer-based pre-trained models for code have been developed and applied to code-related tasks. In this paper, we review the existing literature, examine the suitability of model architectures for different tasks, and look at the…
The increasing reliance on large-scale datasets in machine learning poses significant privacy and ethical challenges, particularly in sensitive domains such as face recognition. Synthetic data generation offers a promising alternative;…
Deep learning models, particularly Transformers, have achieved impressive results in various domains, including time series forecasting. While existing time series literature primarily focuses on model architecture modifications and data…
Graph foundation models face several fundamental challenges including transferability across datasets and data scarcity, which calls into question the very feasibility of graph foundation models. However, despite similar challenges, the…
Graphs are able to model interconnected entities in many online services, supporting a wide range of applications on the Web. This raises an important question: How can we train a graph foundational model on multiple source domains and…
Relational Foundation Models (RFMs) facilitate data-driven decision-making by learning from complex multi-table databases. However, the diverse relational databases needed to train such models are rarely public due to privacy constraints.…
Recently, an intriguing research trend for automatic target recognition (ATR) from synthetic aperture radar (SAR) imagery has arisen: using simulated data to train ATR models is a feasible solution to the issue of inadequate measured data.…
Synthetic augmentation is increasingly used to mitigate data scarcity in financial machine learning, yet its statistical role remains poorly understood. We formalize synthetic augmentation as a modification of the effective training…
Time series foundation models (TSFMs) offer strong zero-shot forecasting via large-scale pre-training, yet fine-tuning remains critical for boosting performance in domains with limited public data. With the growing number of TSFMs,…
[Context] Modern AI applications increasingly process highly structured data, such as 3D meshes and point clouds, where test input generation must preserve both structural and semantic validity. However, existing fuzzing tools and input…