On the Feasibility of Fidelity$^-$ for Graph Pruning

TL;DR

This paper investigates the use of fidelity, a metric for explanation quality in GNNs, as a basis for graph pruning, proposing a new framework that leverages local explanations to create global edge masks.

Contribution

It introduces Fidelity$^-$-inspired Pruning (FiP), a novel framework that constructs global edge masks from local explanations to improve graph pruning efficiency.

Findings

General XAI methods outperform GNN-specific methods in pruning performance.

Fidelity$^-$-based pruning effectively enhances GNN efficiency.

Empirical validation across 7 edge attribution methods.

Abstract

As one of popular quantitative metrics to assess the quality of explanation of graph neural networks (GNNs), fidelity measures the output difference after removing unimportant parts of the input graph. Fidelity has been widely used due to its straightforward interpretation that the underlying model should produce similar predictions when features deemed unimportant from the explanation are removed. This raises a natural question: "Does fidelity induce a global (soft) mask for graph pruning?" To solve this, we aim to explore the potential of the fidelity measure to be used for graph pruning, eventually enhancing the GNN models for better efficiency. To this end, we propose Fidelity$^-$-inspired Pruning (FiP), an effective framework to construct global edge masks from local explanations. Our empirical observations using 7 edge attribution methods demonstrate that, surprisingly, general eXplainable AI methods outperform methods tailored to GNNs in terms of graph pruning performance.