Tech Xplore

HarmonyGNN boosts graph AI accuracy on four tough benchmarks by up to 9.6%

Researchers have demonstrated a new training technique that significantly improves the accuracy of graph neural networks ...
IEEE

Graph Neural Networks for Graphs With Heterophily: A Survey

Abstract: Recent years have witnessed fast developments of graph neural networks (GNNs) that have benefited myriad graph analytic tasks and applications. Most GNNs rely on the homophily assumption ...
GitHub

This repo describes python code and input data files for "Forecasting stock return distributions around the globe with quantile neural networks".

Inputs: describes all the raw inputs to run the code Code description: describes the python code and how to run it Code to figure mapping: provides mapping of figures in the paper to code used to ...
IEEE

Contra Harmonic Mean Labeling of Some Graphs and Python-Based Continuous-Time Neural Networks for Solving the Travelling Salesman Problem in Artificial Intelligence

Abstract: In this paper, we prove Contra Harmonic Mean Labeling for some star related graphs such as $\mathrm{K}_{1, \mathrm{n}}, S(\mathrm{K}_{1, \mathrm{n ...