Efficient Higher-order Subgraph Attribution via Message Passing

TL;DR

This paper introduces linear-time algorithms for higher-order subgraph attribution in GNNs using message passing, significantly improving efficiency and scalability over previous exponential-time methods.

Contribution

The authors develop novel message passing algorithms that enable efficient, linear-time higher-order subgraph attribution for GNN explanations, extending existing methods.

Findings

Algorithms achieve significant speedup in subgraph attribution.

The methods scale well to larger graphs and deeper networks.

Experimental results demonstrate high usefulness and scalability.

Abstract

Explaining graph neural networks (GNNs) has become more and more 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 demonstrate that such exponential complexity can be avoided. In particular, we propose novel algorithms that enable to attribute subgraphs with GNN-LRP in linear-time (w.r.t. the network depth). Our algorithms are derived via message passing techniques that make use of the distributive property, thereby directly computing quantities for higher-order explanations. We further adapt our efficient algorithms to compute a generalization of subgraph attributions that also takes into account the neighboring graph features. Experimental results show the significant acceleration of the proposed algorithms and demonstrate the high usefulness and scalability of our novel generalized subgraph attribution method.