IEEE

The Mixture Graph-A Data Structure for Compressing, Rendering, and Querying Segmentation Histograms

Abstract: In this paper, we present a novel data structure, called the Mixture Graph. This data structure allows us to compress, render, and query segmentation histograms. Such histograms arise when ...
IEEE

GMMDA: Gaussian Mixture Modeling of Graph in Latent Space for Graph Data Augmentation

Abstract: Graph data augmentation (GDA), which manipulates graph structure and/or attributes, has been demonstrated as an effective method for improving the generalization of graph neural networks on ...
Europe PMC

Graph embedding and Gaussian mixture variational autoencoder network for end-to-end analysis of single-cell RNA sequencing data.

Single-cell RNA sequencing (scRNA-seq) is a revolutionary technology to determine the precise gene expression of individual cells and identify cell heterogeneity and subpopulations. However, technical ...
GitHub

Mixture-of-Experts (MoE) for OOD Graph Learning

This repository implements a Mixture-of-Experts (MoE) architecture for improving Out-of-Distribution (OOD) generalization in graph learning tasks, with a focus on graph classification. We will be ...
GitHub

MrSwin/graph-unet-traffic-prediction

GitHub - MrSwin/graph-unet-traffic-prediction: Hybrid UNet model for traffic prediction from traffic movies. The hybrid graph operation is a mixture of CNN and GNN operations to capture pixel topology ...