Complete the Missing Half: Augmenting Aggregation Filtering with Diversification for Graph Convolutional Networks. (arXiv:2008.08844v4 [cs.LG] UPDATED)

The core operation of current Graph Neural Networks (GNNs) is the aggregation
enabled by the graph Laplacian or message passing, which filters the
neighborhood node information. Though effective for various tasks, in this
paper, we show that they are potentially a problematic factor underlying all
GNN methods for learning on certain datasets, as they force the node
representations similar, making the nodes gradually lose their identity and
become indistinguishable. Hence, we augment the aggregation operations with
their dual, i.e. diversification …

aggregation arxiv filtering graph networks