On the Feasibility of Fidelity$^-$ for Graph Pruning
This work addresses graph pruning for GNN efficiency, but it is incremental as it adapts an existing metric rather than introducing a new paradigm.
The paper investigates whether the fidelity metric from GNN explanations can be used for graph pruning, proposing FiP to create global edge masks from local explanations, and finds that general XAI methods outperform GNN-specific ones in pruning performance.
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.