AI RESEARCH
Efficient Higher-order Subgraph Attribution via Message Passing
arXiv CS.LG
•
ArXi:2605.22385v1 Announce Type: new Explaining graph neural networks (GNNs) has become and important recently. Higher-order interpretation schemes, such as GNN-LRP (layer-wise relevance propagation for GNN), emerged as powerful tools for unraveling how different features interact thereby contributing to explaining GNNs. GNN-LRP gives a relevance attribution of walks between nodes at each layer, and the subgraph attribution is expressed as a sum over exponentially many such walks. In this work, we nstrate that such exponential complexity can be avoided.