Triple Sparsification of Graph Convolutional Networks without Sacrificing the Accuracy
This work addresses efficiency challenges in graph learning tasks, offering a method to reduce resource usage while maintaining performance, though it appears incremental as it builds on existing sparsification techniques.
The paper tackles the problem of high computational and memory costs in Graph Neural Networks (GNNs) as graph sizes and model depths increase, by developing a SparseGCN pipeline that achieves up to 11.6% additional sparsity in the embedding matrix without accuracy loss on benchmark datasets.
Graph Neural Networks (GNNs) are widely used to perform different machine learning tasks on graphs. As the size of the graphs grows, and the GNNs get deeper, training and inference time become costly in addition to the memory requirement. Thus, without sacrificing accuracy, graph sparsification, or model compression becomes a viable approach for graph learning tasks. A few existing techniques only study the sparsification of graphs and GNN models. In this paper, we develop a SparseGCN pipeline to study all possible sparsification in GNN. We provide a theoretical analysis and empirically show that it can add up to 11.6\% additional sparsity to the embedding matrix without sacrificing the accuracy of the commonly used benchmark graph datasets.