The general consensus for an Graph-AE is to train against the dense adjacency matrix. However, you only need a dense output. In contrast, the input graph can be sparse. We have an example of this, see ...

PyG (PyTorch Geometric) is a library built upon PyTorch to easily write and train Graph Neural Networks (GNNs) for a wide range of applications related to structured data. It consists of various ...

In this paper, we propose a progressive two-step algorithm called GIFTS to accelerate GCN inference on CPUs by making use of the dynamic sparsity in the feature matrix and the static sparsity in the ...

In this paper, we describe three graph theoretic heuristics that attempt to determine an optimal planar adjacency graph from a REL chart. Our computational experience suggests that these methods can ...