Authors: Tanvir Hossain, Khaled Mohammed Saifuddin, Muhammad Ifte Khairul Islam, Farhan Tanvir, Esra Akbas
Abstract: Graph Neural Network (GNN) achieves great success for node-level and
graph-level tasks via encoding meaningful topological structures of networks in
various domains, ranging from social to biological networks. However, repeated
aggregation operations lead to excessive mixing of node representations,
particularly in dense regions with multiple GNN layers, resulting in nearly
indistinguishable embeddings. This phenomenon leads to the oversmoothing
problem that hampers downstream graph analytics tasks. To overcome this issue,
we propose a novel and flexible truss-based graph sparsification model that
prunes edges from dense regions of the graph. Pruning redundant edges in dense
regions helps to prevent the aggregation of excessive neighborhood information
during hierarchical message passing and pooling in GNN models. We then utilize
our sparsification model in the state-of-the-art baseline GNNs and pooling
models, such as GIN, SAGPool, GMT, DiffPool, MinCutPool, HGP-SL, DMonPool, and
AdamGNN. Extensive experiments on different real-world datasets show that our
model significantly improves the performance of the baseline GNN models in the
graph classification task.
Source: http://arxiv.org/abs/2407.11928v1
