Conditional Local Feature Encoding for Graph Neural Networks

arXiv:2405.04755v1 Announce Type: new
Abstract: Graph neural networks (GNNs) have shown great success in learning from graph-based data. The key mechanism of current GNNs is message passing, where a node's feature is updated based on the information passing from its local neighbourhood. A limitation of this mechanism is that node features become increasingly dominated by the information aggregated from the neighbourhood as we use more rounds of message passing. Consequently, as the GNN layers become deeper, adjacent node features tends …

abstract arxiv become cs.lg current data encoding feature features gnns graph graph-based graph neural networks information key networks neural networks node success the information the key type