Enabling Accelerators for Graph Computing

arXiv:2312.10561v2 Announce Type: replace-cross
Abstract: The advent of Graph Neural Networks (GNNs) has revolutionized the field of machine learning, offering a novel paradigm for learning on graph-structured data. Unlike traditional neural networks, GNNs are capable of capturing complex relationships and dependencies inherent in graph data, making them particularly suited for a wide range of applications including social network analysis, molecular chemistry, and network security. GNNs, with their unique structure and operation, present new computational challenges compared to conventional neural networks. …

abstract accelerators applications arxiv computing cs.ai cs.ar cs.dc cs.lg data dependencies enabling gnns graph graph computing graph data graph neural networks machine machine learning making networks neural networks novel paradigm relationships structured data them type