This situation poses a considerable challenge for newcomers, hindering their ability to grasp a comprehensive understanding of the workflows, computational patterns, communication strategies, and optimization techniques employed in distributed GNN training.
This paper proposes a post-disaster cyber-physical interdependent restoration scheduling (CPIRS) framework for active distribution networks (ADN) where the simultaneous damages on cyber and physical networks are considered.
Thereby, we propose to drop redundancy and improve efficiency of training large-scale graphs with GNNs, by rethinking the inherent characteristics in a graph.
Heterogeneous graph neural networks (HGNNs) have powerful capability to embed rich structural and semantic information of a heterogeneous graph into node representations.
Ranked #6 on Node Property Prediction on ogbn-mag
Graph neural network (GNN) has been demonstrated to be a powerful model in many domains for its effectiveness in learning over graphs.
Next, we provide comparisons from aspects of the efficiency and characteristics of these methods.
Extensive experiments show that our method is universal to mainstream sampling algorithms and helps significantly reduce the training time, especially in large-scale graphs.
Graph Convolutional Networks (GCNs) have received significant attention from various research fields due to the excellent performance in learning graph representations.
Graph convolutional network (GCN) emerges as a promising direction to learn the inductive representation in graph data commonly used in widespread applications, such as E-commerce, social networks, and knowledge graphs.
In this work, we first characterize the hybrid execution patterns of GCNs on Intel Xeon CPU.
Distributed, Parallel, and Cluster Computing