为图推理中测试节点邻居重要性评估提供高效可解释的量化方法
Shapley-Guided Utility Learning for Effective Graph Inference Data Valuation
- 结合特征与模型特性的可迁移特征，不依赖真实标签预测测试准确率
- 利用谢林值预处理，直接优化谢林值预测，降低计算开销
- 在多种图数据集上表现优于现有方法，适合需解释性的图学习场景
图神经网络在各类图机器学习任务中表现卓越，但因缺乏测试标签，评估测试节点邻居的重要性仍属空白。为此，我们提出一种名为谢林值引导的效用学习（SGUL）的新框架，用于图推理中的数据价值评估。SGUL创新性地融合可迁移的数据特定与模型特定特征，无需真实标签即可近似测试准确率。通过将谢林值作为预处理步骤，并以特征谢林值为输入，该方法实现谢林值预测的直接优化，同时降低计算成本。相比现有方法，SGUL克服了泛化能力差和间接优化等关键缺陷。在多种图数据集上的实验表明，无论在归纳还是直推设置下，SGUL均持续优于基线方法。本方法提供了高效、精准且可解释的测试时邻居价值量化方案。
原文摘要 · Abstract (English)
Graph Neural Networks (GNNs) have demonstrated remarkable performance in various graph-based machine learning tasks, yet evaluating the importance of neighbors of testing nodes remains largely unexplored due to the challenge of assessing data importance without test labels. To address this gap, we propose Shapley-Guided Utility Learning (SGUL), a novel framework for graph inference data valuation. SGUL innovatively combines transferable data-specific and modelspecific features to approximate test accuracy without relying on ground truth labels. By incorporating Shapley values as a preprocessing step and using feature Shapley values as input, our method enables direct optimization of Shapley value prediction while reducing computational demands. SGUL overcomes key limitations of existing methods, including poor generalization to unseen test-time structures and indirect optimization. Experiments on diverse graph datasets demonstrate that SGUL consistently outperforms existing baselines in both inductive and transductive settings. SGUL offers an effective, efficient, and interpretable approach for quantifying the value of test-time neighbors.
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。