<ul><li>Graph Neural Networks (GNNs) are widely used in graph data mining tasks.</li><li>Traditional GNNs face limitations in terms of over-smoothing and over-squashing, which limit the receptive field in message passing processes.</li><li>To address these limitations, a new approach called Structure-aware Multi-token Graph Transformer (Tokenphormer) is proposed.</li><li>Tokenphormer generates multiple tokens to capture local and structural information, exploring global information at different levels of granularity.</li></ul>

Tokenphormer: Structure-aware Multi-token Graph Transformer for Node Classification

Discover more