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 ...
Scientific Research Publishing

Lin, J., Zhao, Y., Huang, W., Liu, C. and Pu, H. (2020) Domain Knowledge Graph-Based Research Progress of Knowledge Representation. Neural Computing and Applications, 33, 681-690.

ABSTRACT: Knowledge Graph (KG) and neural network (NN) based Question-answering (QA) systems have evolved into the realm of intelligent information retrieval as they have been able to reach a high ...
Quanta Magazine

New Proof Settles Decades-Old Bet About Connected Networks

According to mathematical legend, Peter Sarnak and Noga Alon made a bet about optimal graphs in the late 1980s. They’ve now both been proved wrong. It started with a bet. In the late 1980s, at a ...
IEEE

Torsion Graph Neural Networks

Abstract: Geometric deep learning (GDL) models have demonstrated a great potential for the analysis of non-Euclidian data. They are developed to incorporate the geometric and topological information ...
MIT Technology Review

The next generation of neural networks could live in hardware

Researchers have devised a way to make computer vision systems more efficient by building networks out of computer chips’ logic gates. Networks programmed directly into computer chip hardware can ...