Related papers: SEDGE: Structural Extrapolated Data Generation

As diffusion probabilistic models (DPMs) become central to Generative AI (GenAI), understanding their memorization behavior is essential for evaluating risks such as data leakage, copyright infringement, and trustworthiness. While prior…

In this paper, we propose a novel ensembling technique for deep neural networks, which is able to drastically reduce the required memory compared to alternative approaches. In particular, we propose to extract multiple sub-networks from a…

We define a general class of network formation models, Statistical Exponential Random Graph Models (SERGMs), that nest standard exponential random graph models (ERGMs) as a special case. We provide the first general results on when these…

Search-Augmented Generative Engines (SAGE) have emerged as a new paradigm for information access, bridging web-scale retrieval with generative capabilities to deliver synthesized answers. This shift has fundamentally reshaped how web…

In real world domains, most graphs naturally exhibit a hierarchical structure. However, data-driven graph generation is yet to effectively capture such structures. To address this, we propose a novel approach that recursively generates…

Data for pretraining machine learning models often consists of collections of heterogeneous datasets. Although training on their union is reasonable in agnostic settings, it might be suboptimal when the target domain -- where the model will…

Mobile edge generation (MEG) is an emerging technology that allows the network to meet the challenging traffic load expectations posed by the rise of generative artificial intelligence~(GAI). A novel MEG model is proposed for deploying GAI…

Recent work has shown generative adversarial networks (GANs) can generate highly realistic images, that are often indistinguishable (by humans) from real images. Most images so generated are not contained in the training dataset, suggesting…

Dataset distillation aims to synthesize a small dataset from a large dataset, enabling the model trained on it to perform well on the original dataset. With the blooming of large language models and multimodal large language models, the…

Synthetic power grids enable secure, real-world energy system simulations and are crucial for algorithm testing, resilience assessment, and policy formulation. We propose a novel method for the generation of synthetic transmission power…

There is significant growth and interest in the use of synthetic data as an enabler for machine learning in environments where the release of real data is restricted due to privacy or availability constraints. Despite a large number of…

We study the functional task of deep learning image classification models and show that image classification requires extrapolation capabilities. This suggests that new theories have to be developed for the understanding of deep learning as…

Data synthesis is gaining momentum as a privacy-enhancing technology. While single-table tabular data generation has seen considerable progress, current methods for multi-table data often lack the flexibility and expressiveness needed to…

Synthetically generated data can improve privacy, fairness, and data accessibility; however, it can be challenging in specialized scenarios such as survival analysis. One key challenge in this setting is censoring, i.e., the timing of an…

We study the knowledge extrapolation problem to embed new components (i.e., entities and relations) that come with emerging knowledge graphs (KGs) in the federated setting. In this problem, a model trained on an existing KG needs to embed…

Deep learning-based medical image processing algorithms require representative data during development. In particular, surgical data might be difficult to obtain, and high-quality public datasets are limited. To overcome this limitation and…

We propose a semantically-aware novel paradigm to perform image extrapolation that enables the addition of new object instances. All previous methods are limited in their capability of extrapolation to merely extending the already existing…

Data generation is a fundamental research problem in data management due to its diverse use cases, ranging from testing database engines to data-specific applications. However, real-world entities often involve complex interactions that…

Text-to-image generation requires large amount of training data to synthesizing high-quality images. For augmenting training data, previous methods rely on data interpolations like cropping, flipping, and mixing up, which fail to introduce…

Graph generation is integral to various engineering and scientific disciplines. Nevertheless, existing methodologies tend to overlook the generation of edge attributes. However, we identify critical applications where edge attributes are…