Related papers: Generating Synthetic Fair Syntax-agnostic Data by …

Dataset distillation has emerged as an effective strategy, significantly reducing training costs and facilitating more efficient model deployment. Recent advances have leveraged generative models to distill datasets by capturing the…

Language models excel at generating coherent text, and model compression techniques such as knowledge distillation have enabled their use in resource-constrained settings. However, these models can be biased in multiple ways, including the…

Frontier commercial generative models face a growing threat from distillation, whereby a distiller harvests generated responses and trains a competing model of its own at drastically lower cost. Existing defenses either rely on modifying…

Iterative generative models, such as noise conditional score networks and denoising diffusion probabilistic models, produce high quality samples by gradually denoising an initial noise vector. However, their denoising process has many…

Dataset distillation has emerged as a strategy to overcome the hurdles associated with large datasets by learning a compact set of synthetic data that retains essential information from the original dataset. While distilled data can be used…

A generative modeling framework is proposed that combines diffusion models and manifold learning to efficiently sample data densities on manifolds. The approach utilizes Diffusion Maps to uncover possible low-dimensional underlying (latent)…

Training deep neural networks has become increasingly demanding, requiring large datasets and significant computational resources, especially as model complexity advances. Data distillation methods, which aim to improve data efficiency,…

To alleviate the reliance of deep neural networks on large-scale datasets, dataset distillation aims to generate compact, high-quality synthetic datasets that can achieve comparable performance to the original dataset. The integration of…

Data-Free Robustness Distillation (DFRD) aims to transfer the robustness from the teacher to the student without accessing the training data. While existing methods focus on overall robustness, they overlook the robust fairness issues,…

In distributed computing environments, collaborative machine learning enables multiple clients to train a global model collaboratively. To preserve privacy in such settings, a common technique is to utilize frequent updates and…

Network quantization is an essential procedure in deep learning for development of efficient fixed-point inference models on mobile or edge platforms. However, as datasets grow larger and privacy regulations become stricter, data sharing…

Recent approaches have shown promises distilling diffusion models into efficient one-step generators. Among them, Distribution Matching Distillation (DMD) produces one-step generators that match their teacher in distribution, without…

With the increasing reliance on automated decision making, the issue of algorithmic fairness has gained increasing importance. In this paper, we propose a Generative Adversarial Network for tabular data generation. The model includes two…

There have been tremendous efforts over the past decades dedicated to the generation of realistic graphs in a variety of domains, ranging from social networks to computer networks, from gene regulatory networks to online transaction…

Layout Generation aims to synthesize plausible arrangements from given elements. Currently, the predominant methods in layout generation are Generative Adversarial Networks (GANs) and diffusion models, each presenting its own set of…

The aim of dataset distillation is to encode the rich features of an original dataset into a tiny dataset. It is a promising approach to accelerate neural network training and related studies. Different approaches have been proposed to…

Acquiring high-quality data for training discriminative models is a crucial yet challenging aspect of building effective predictive systems. In this paper, we present Diffusion Inversion, a simple yet effective method that leverages the…

Multi-weather image restoration has witnessed incredible progress, while the increasing model capacity and expensive data acquisition impair its applications in memory-limited devices. Data-free distillation provides an alternative for…

Large pretrained diffusion models have significantly enhanced the quality of generated videos, and yet their use in real-time streaming remains limited. Autoregressive models offer a natural framework for sequential frame synthesis but…

Classifier-free guided diffusion models have recently been shown to be highly effective at high-resolution image generation, and they have been widely used in large-scale diffusion frameworks including DALLE-2, Stable Diffusion and Imagen.…