Graph-related applications have experienced significant growth in academ...
Heterogeneous graph neural networks (HGNNs) have emerged as powerful
alg...
Graph neural networks (GNNs) have been demonstrated to be a powerful
alg...
Large-scale graphs are ubiquitous in real-world scenarios and can be tra...
Heterogeneous graph neural networks (HGNNs) deliver powerful capacity in...
Limited by the memory capacity and compute power, singe-node graph
convo...
Heterogeneous graph neural networks (HGNNs) deliver the powerful capabil...
Graph neural network (GNN) has been demonstrated to be a powerful model ...
Previous graph analytics accelerators have achieved great improvement on...
Graph neural networks (GNNs) have been a hot spot of recent research and...
Sampling is a critical operation in the training of Graph Neural Network...
The state-of-the-art driving automation system demands extreme computati...
Graph Convolutional Networks (GCNs) have received significant attention ...
Face recognition is widely used in the scene. However, different visual
...
Many meta-learning methods which depend on a large amount of data and mo...
Graph convolutional neural networks (GCNs) have achieved state-of-the-ar...
In this work, we first characterize the hybrid execution patterns of GCN...
We analyze that different methods based channel or position attention
me...
Weakly supervised object detection (WSOD) focuses on training object det...