Nature

Hypergraph Neural Network Methods in Graph-Based Learning articles from across Nature Portfolio

Hypergraph Neural Networks (HGNNs) have been significantly successful in higher-order tasks. However, recent study have shown that they are also vulnerable to adversarial attacks like Graph Neural ...
EurekAlert!

Molecular merged hypergraph neural network for explainable solvation Gibbs free energy prediction

Background: Molecular interactions are central to numerous challenges in chemistry and the life sciences. Whether in solute–solvent dissolution, adverse drug–drug interactions, or protein complex ...
Semiconductor Engineering

Hypergraph-based Techniques To Map Spiking Neural Networks on Neuromorphic HW (Politecnico di Milano)

A new technical paper titled “A Case for Hypergraphs to Model and Map SNNs on Neuromorphic Hardware” was published by researchers at Politecnico di Milano. “Executing Spiking Neural Networks (SNNs) on ...
english.cas

Dynamic Clustering Accelerates Neural Networks on Resource-Constrained Platforms

Called Dynamic Clustering for Channel Pruning (DCCP), the method reduced the floating-point operations of ResNet-50 by 68.52% ...