<ul data-eligibleForWebStory="false"><li>Subgraph GNNs have emerged to enhance the expressiveness of Graph Neural Networks (GNNs) by processing bags of subgraphs.</li><li>A new approach called HyMN is proposed to reduce the computational cost of Subgraph GNNs by leveraging walk-based centrality measures.</li><li>HyMN samples a small number of relevant subgraphs to reduce bag size, increasing efficiency without sacrificing performance.</li><li>Experimental results show that HyMN effectively balances expressiveness, efficiency, and downstream performance, making Subgraph GNNs applicable to larger graphs.</li></ul>

Balancing Efficiency and Expressiveness: Subgraph GNNs with Walk-Based Centrality

Discover more