用博弈论方法解释时序图神经网络的预测依据
Explaining Temporal Graph Predictions With Shapley Values
- 基于谢林值和欧文值，从事件与特征层级解析模型决策
- 在多个数据集上优于现有方法，揭示了时间戳提取缺陷
- 适合关注模型可解释性与潜在偏差的研究者
时序图神经网络（TGNN）因结合空间与时间信息而表现出优异预测性能，但其如何利用信息进行预测尚不明确，可能导致模型错误或偏见。本文提出两种新型模型无关的局部解释方法：一是基于核SHAP算法的事件级（边级）谢林值解释器，用于估算单个时序事件的贡献得分；二是特征级谢林值解释器，将事件级谢林值分解为欧文值，揭示事件与其特征之间的层次依赖关系。所提方法在不同指标与数据集上均优于当前最优解释器。此外，特征解释器发现一种常用TGAT实现存在实际时间戳提取错误，有助于理解其在极稀疏场景下性能下降的原因。
原文摘要 · Abstract (English)
Temporal Graph Neural Networks (TGNNs) have become increasingly popular in recent years due to their superior predictive performance by combining both spatial and temporal information. However, how these models utilize the information to make predictions is rather unexplored, leading to potentially faulty or biased models. This work introduces two novel model-agnostic explainers for local explanations of TGNNs based on Shapley and Owen values. The first method, an event-level (edge-level) Shapley explainer, applies the KernelSHAP algorithm to estimate contribution scores for individual temporal events, providing interpretable descriptions for model behavior. The second, a feature-level Shapley explainer, extends this framework by decomposing event-level Shapley values into Owen values, and thereby uncovers hierarchical dependencies of the event and its features. The explainers outperform SOTA explainers on different metrics and datasets. Additionally, the Feature Explainer reveals a faulty extraction of actual timestamps of a commonly used TGAT implementation, helping to further understand performance drops on very sparse explanations.
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。