一种用于图神经网络中精确奥曼-夏普利归因的多项式架构-归因协同设计框架
A Polynomial Architecture-Attribution Co-Design Framework for Exact Aumann-Shapley Attribution in GNNs
- Institute of Artificial Intelligence Innovation and Industry, Fudan University（复旦大学人工智能创新与产业研究院）
- Shanghai Academy of AI for Science（上海人工智能科学研究院）
- Human Phenome Institute, Fudan University（复旦大学人类表型组研究院）
- School of Information and Communication Engineering, Communication University of China（中国传媒大学信息与通信工程学院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
研究图神经网络的特征级和节点级解释，提出APEX框架，通过PolyGIN使归因积分可精确计算，实验表明该框架能保持预测性能，提高归因保真度并减少评估次数。
AI中文摘要：
我们通过奥曼-夏普利归因的视角研究图神经网络（GNN）的特征级和节点级解释。诸如积分梯度等路径积分方法提供了归因的公理公式，但在深度GNN中的实际应用通常依赖于对路径积分的有限样本数值近似，需要在求积误差和计算成本之间进行权衡。本文提出了APEX，一种模型-归因协同设计框架，在多项式GNN架构下使归因积分可精确计算。关键组件是PolyGIN，一种GIN风格的图网络，其消息传递、归一化和变换操作对标量模型分数（如softmax前对数its）保持有界多元多项式形式。我们表明，对于具有L个多项式变换块的PolyGIN，沿归因路径的导数度数至多为2^L - 1。因此，高斯-勒让德求积可以用2^(L - 1)个确定性评估点精确评估奥曼-夏普利路径积分，达到浮点精度。在合成和真实世界图基准上的实验表明，PolyGIN保持有竞争力的预测性能，而完整的APEX框架比比较基线实现更高的归因保真度，并大幅减少路径积分所需的评估次数。
英文摘要：
We study feature-level and node-level explanations for graph neural networks (GNNs) through the lens of Aumann-Shapley attribution. Path-integral methods such as Integrated Gradients provide an axiomatic formulation of attribution, but their practical use in deep GNNs typically relies on finite-sample numerical approximations to the path integral, requiring a trade-off between quadrature error and computational cost. This paper proposes APEX, a model-attribution co-design framework that makes the attribution integral exactly computable under a polynomial GNN architecture. The key component is PolyGIN, a GIN-style graph network whose message-passing, normalization, and transformation operations preserve a bounded multivariate polynomial form for scalar model scores, such as pre-softmax logits. We show that, for a PolyGIN with $L$ polynomial transformation blocks, the derivative along the attribution path has degree at most $2^L-1$. Therefore, Gauss--Legendre quadrature can evaluate the Aumann--Shapley path integral exactly, up to floating-point precision, with $2^{L-1}$ deterministic evaluation points. The resulting attributions can be computed at the feature level and then aggregated into node-level scores while preserving completeness. Experiments on synthetic and real-world graph benchmarks show that PolyGIN maintains competitive predictive performance, while the complete APEX framework achieves higher attribution fidelity than the compared baselines and substantially reduces the number of evaluations required for path integration.
