First is Node2Vec, a popular graph embedding algorithm that uses neural networks to learn continuous feature representations for nodes, which can then be used for downstream machine learning tasks.

NetworkX isn’t the first graph library Nvidia has supported with RAPIDS. The company has offered cuGraph on RAPIDS since it launched back in 2018, Becker says. CuGraph is still a valuable tool, ...

The team proposed a Python-based library named XGCN, aiming at helping users quickly build and run large-scale GNNs in a single-machine environment.

Research team led by Chuliang Weng introduces D2-GCN, a groundbreaking disentangled graph convolutional network that dynamically adjusts feature channels for enhanced node representation ...