Research Article
DAG Scheduling with Communication Delays Based on Graph Convolutional Neural Network
Figure 5
The scheduling length of the DAG in Figure 2 based on three representative neural networks and our TLGC method. The -axis means the time and the -axis stands for the three available processors.
(a) seq2seq |
(b) GAT |
(c) GraphSAGE |
(d) TLGC |