IEEE

Multigranularity Deep Graph Convolutional Neural Network Node Clustering Leveraging Spatial Information

Abstract: In the era of information explosion, clustering analysis of graph-structured data and empty graph-structured data is of great significance for extracting the intrinsic value of data. From ...
IEEE

A Multi-Clustering Aggregation Method for Initializing Node Representations in Featureless Graphs

Abstract: The non-Euclidean nature of graphs made them inaccessible to standard deep learning techniques that rely on fixed-size, ordered inputs. Graph Neural Networks (GNNs) are essential for serving ...
GitHub

ML SDK Scenario Runner

The Scenario Runner is an application that executes shader and neural network graph workloads through Vulkan® or the ML extensions for Vulkan®. The Scenario Runner acts as a validation and performance ...
GitHub

Boosting Graph Neural Networks via Adaptive Knowledge Distillation

This repository contains the official implementation of the paper "Boosting Graph Neural Networks via Adaptive Knowledge Distillation". This work proposes a novel knowledge distillation framework for ...