4 papers
A Survey of Graph Pre-processing Methods: From Algorithmic to Hardware Perspectives
Zhengyang Lv, Mingyu Yan, Xin Liu +4
Graph-related applications have experienced significant growth in academia and industry, driven by the powerful representation capabilities of graph. However, efficiently executing…
Rethinking Efficiency and Redundancy in Training Large-scale Graphs
Xin Liu, Xunbin Xiong, Mingyu Yan +4
Large-scale graphs are ubiquitous in real-world scenarios and can be trained by Graph Neural Networks (GNNs) to generate representation for downstream tasks. Given the abundant inf…
Characterizing and Understanding HGNNs on GPUs
Mingyu Yan, Mo Zou, Xiaocheng Yang +4
Heterogeneous graph neural networks (HGNNs) deliver powerful capacity in heterogeneous graph representation learning. The execution of HGNNs is usually accelerated by GPUs. Therefo…
Multi-node Acceleration for Large-scale GCNs
Gongjian Sun, Mingyu Yan, Duo Wang +5
Limited by the memory capacity and compute power, singe-node graph convolutional neural network (GCN) accelerators cannot complete the execution of GCNs within a reasonable amount…