Inference queries have been routinely issued to graph machine learning models such as graph neural networks (GNNs) for various network analytical tasks. Nevertheless, GNN outputs are often hard to interpret comprehensively. Existing methods typically conform to individual pre-defined explainability measures (such as fidelity), which often leads to biased, ``one-side'' interpretations. This paper introduces skyline explanation, a new paradigm that interprets GNN outputs by simultaneously optimizing multiple explainability measures of users' interests. (1) We propose skyline explanations as a Pareto set of explanatory subgraphs that dominate others over multiple explanatory measures. We formulate skyline explanation as a multi-criteria optimization problem, and establish its hardness results. (2) We design efficient algorithms with an onion-peeling approach, which strategically prioritizes nodes and removes unpromising edges to incrementally assemble skyline explanations. (3) We also develop an algorithm to diversify the skyline explanations to enrich the comprehensive interpretation. (4) We introduce efficient parallel algorithms with load-balancing strategies to scale skyline explanation for large-scale GNN-based inference. Using real-world and synthetic graphs, we experimentally verify our algorithms' effectiveness and scalability.

翻译：推理查询常被用于图机器学习模型（如图神经网络GNN）以执行各类网络分析任务。然而，GNN的输出往往难以全面解读。现有方法通常遵循单一预定义的可解释性度量（如保真度），这常导致带有偏见的“片面”解释。本文提出天际线解释这一新范式，通过同时优化用户关注的多个可解释性度量来解读GNN输出。（1）我们将天际线解释定义为帕累托解释子图集，其在多个解释度量上优于其他解释。我们将天际线解释建模为多目标优化问题，并证明其计算复杂性。（2）我们设计基于洋葱剥离策略的高效算法，通过优先级节点排序和逐步剔除无效边来增量构建天际线解释。（3）我们还开发了算法以增强天际线解释的多样性，从而丰富全面解读。（4）我们提出采用负载均衡策略的并行算法，以支持基于GNN的大规模推理任务的天际线解释扩展。通过真实世界与合成图数据实验，我们验证了算法的有效性与可扩展性。