3 papers
cs.LG2025
Cross-Domain Graph Data Scaling: A Showcase with Diffusion Models
Wenzhuo Tang, Haitao Mao, Danial Dervovic +4
Models for natural language and images benefit from data scaling behavior: the more data fed into the model, the better they perform. This 'better with more' phenomenon enables the…
cs.LG2025
Theoretical guarantees for the advantage of GNNs over NNs in generalizing bandlimited functions on Euclidean cubes
A. Martina Neuman, Rongrong Wang, Yuying Xie
Graph Neural Networks (GNNs) have emerged as formidable resources for processing graph-based information across diverse applications. While the expressive power of GNNs has traditi…
cs.IT2024
Convolutional dynamical sampling and some new results
Longxiu Huang, A. Martina Neuman, Sui Tang +1
In this work, we explore the dynamical sampling problem on driven by a convolution operator defined by a convolution kernel. This problem is inspired by the ne…