SGS-GNN: A Supervised Graph Sparsification method for Graph Neural Networks

TL;DR

SGS-GNN introduces a supervised graph sparsification method that learns optimal edge sampling to reduce computational costs while maintaining or improving GNN accuracy, especially on heterophilic graphs.

Contribution

It presents a novel supervised sparsifier that adaptively learns edge sampling probabilities, enhancing GNN performance and efficiency on large, diverse graphs.

Findings

Improves F1-score by 4% with only 20% edges retained.

Outperforms state-of-the-art sparsification methods by 4-7% in F1-score.

Requires about half the epochs to converge compared to fixed distribution sparsifiers.

Abstract

We propose SGS-GNN, a novel supervised graph sparsifier that learns the sampling probability distribution of edges and samples sparse subgraphs of a user-specified size to reduce the computational costs required by GNNs for inference tasks on large graphs. SGS-GNN employs regularizers in the loss function to enhance homophily in sparse subgraphs, boosting the accuracy of GNNs on heterophilic graphs, where a significant number of the neighbors of a node have dissimilar labels. SGS-GNN also supports conditional updates of the probability distribution learning module based on a prior, which helps narrow the search space for sparse graphs. SGS-GNN requires fewer epochs to obtain high accuracies since it learns the search space of subgraphs more effectively than methods using fixed distributions such as random sampling. Extensive experiments using 33 homophilic and heterophilic graphs demonstrate the following: (i) with only 20% of edges retained in the sparse subgraphs, SGS-GNN improves the F1-scores by a geometric mean of 4% relative to the original graph; on heterophilic graphs, the prediction accuracy is better up to 30%. (ii) SGS-GNN outperforms state-of-the-art methods with improvement in F1-scores of 4-7% in geometric mean with similar sparsities in the sampled subgraphs, and (iii) compared to sparsifiers that employ fixed distributions, SGS-GNN requires about half the number of epochs to converge.