用张量网络高效计算图结构输入的贡献度与交互关系
TN-SHAP-G: Graph-Structured Tensor Network Surrogates for Shapley Values and Interactions
- 构建图对齐的张量网络代理模型，压缩输入空间
- 仅需少量查询即可精准恢复一阶及高阶贡献值
- 适合分子等图结构数据的可解释性分析
Shapley值是黑箱模型中分配输入变量重要性与交互关系的常用工具，但其计算涉及定义在指数级子集空间上的函数。我们提出TN-SHAP-G框架，利用图结构输入的内在规律，高效计算Shapley值与高阶交互指数。给定一个预测器和固定掩码方案，该框架学习一个紧凑、图对齐的多重线性代理模型，以张量网络形式表示，其拓扑结构与输入图一致。训练仅需少量模型查询，之后可通过多重线性扩展确定性恢复一阶与高阶Shapley指数，无需额外查询或蒙特卡洛采样。在分子基准测试中，所学分解在小图上与精确值高度一致，并可高效扩展至大图，传统采样方法在此已不可行。
原文摘要 · Abstract (English)
Shapley values are a widely used tool for attributing importance and interactions among input variables in black-box models, but their computation involves a function defined over an exponentially large space of subsets. We propose TN-SHAP-G, a framework that exploits structure in graph-structured inputs to compute Shapley values and higher-order interaction indices efficiently. Given a predictor and a fixed masking scheme, TN-SHAP-G learns a compact, graph-aligned multilinear surrogate that approximates the masked-input behavior, represented as a tensor network whose topology mirrors the input graph. Once trained from a small number of oracle queries, the surrogate enables deterministic recovery of first- and higher-order Shapley indices via the multilinear extension, without additional model queries or Monte Carlo variance. Experiments on molecular benchmarks show that the learned factorization closely matches exact Shapley values on small graphs and scales efficiently to larger graphs where sampling-based methods become infeasible.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。