GMAN用图结构建模时间序列，兼顾精度与可解释性。
Graph Mixing Additive Networks
- 将时间序列转为有向图，用增强版图神经网络建模
- 在死亡率预测和假新闻检测上超越黑箱模型
- 支持特征、节点、图三级可解释性，适合医疗等高要求场景
我们提出GMAN，一种灵活、可解释且表达能力强的框架，将图神经加法网络（GNAN）扩展至稀疏时间序列数据集。GMAN将每个时变轨迹表示为有向图，并对每个图应用更丰富、更具表达力的GNAN。用户可通过分组特征和图来控制可解释性与表达力之间的权衡，并提供特征、节点和图级别的可解释性。在真实世界数据集上的实验表明，包括从血液检测中预测死亡率和假新闻检测，GMAN在性能上优于强健的非可解释黑箱基线，同时提供可操作且与领域对齐的解释。
原文摘要 · Abstract (English)
We introduce GMAN, a flexible, interpretable, and expressive framework that extends Graph Neural Additive Networks (GNANs) to learn from sets of sparse time-series data. GMAN represents each time-dependent trajectory as a directed graph and applies an enriched, more expressive GNAN to each graph. It allows users to control the interpretability-expressivity trade-off by grouping features and graphs to encode priors, and it provides feature, node, and graph-level interpretability. On real-world datasets, including mortality prediction from blood tests and fake-news detection, GMAN outperforms strong non-interpretable black-box baselines while delivering actionable, domain-aligned 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。