@techreport{oai:ipsj.ixsq.nii.ac.jp:00227130,
 author = {Chen, Zhuang and Peng, Chen and Xin, Liu and Satoshi, Matsuoka and Toshio, Endo and Mohamed, Wahib and Chen, Zhuang and Peng, Chen and Xin, Liu and Satoshi, Matsuoka and Toshio, Endo and Mohamed, Wahib},
 issue = {19},
 month = {Jul},
 note = {Graph Convolutional Networks (GCNs) are widely used across diverse domains. However, training distributed full-batch GCNs on graphs presents challenges due to inefficient memory access patterns and the high communication overhead caused by the graph's irregular structures. In this paper, we propose efficient aggregation operators designed for irregular memory access patterns. Additionally, we employ a pre- and delayed-aggregation approach and leverage half-precision communication to reduce communication costs. By combining these techniques, we have developed an efficient and scalable GCN training framework specifically designed for distributed systems. Experimental results on several graph datasets demonstrate that our proposed method achieves a remarkable speedup of up to 4.75x compared to the state-of-the-art method on the ABCI supercomputer., Graph Convolutional Networks (GCNs) are widely used across diverse domains. However, training distributed full-batch GCNs on graphs presents challenges due to inefficient memory access patterns and the high communication overhead caused by the graph's irregular structures. In this paper, we propose efficient aggregation operators designed for irregular memory access patterns. Additionally, we employ a pre- and delayed-aggregation approach and leverage half-precision communication to reduce communication costs. By combining these techniques, we have developed an efficient and scalable GCN training framework specifically designed for distributed systems. Experimental results on several graph datasets demonstrate that our proposed method achieves a remarkable speedup of up to 4.75x compared to the state-of-the-art method on the ABCI supercomputer.},
 title = {Scalable Training of Graph Convolutional Networks on Supercomputers},
 year = {2023}
}