用短时模式特征提升图神经网络预测能力，效果显著且通用。
Temporal Motif Signatures for Temporal Graph Neural Networks
- 设计13维模式特征，捕捉重复、互惠、三角流等短期互动模式
- 在MOOC数据上，仅4个星型计数特征就接近静态GNN的性能上限
- 适合作为通用增强模块，适用于各类时间图任务
真实的时间交互流中存在可预测的短时模式结构——重复性、互惠性、星型多样性、三角流——而传统时间图神经网络常无法有效利用这些特征。我们在MOOC交互预测任务中验证：仅需一个包含4个过去窗口星型计数的小特征集，即可实现对强大静态GNN的显著超越。在多种真实与合成时间数据集上，我们发现模式活跃度稳定沿三个尺度不变轴分布（二元近期性/互惠性、星型多样性、三角流），据此设计了一个13维、无泄漏、候选局部的模式特征映射 h(u, v, t)，可线性嵌入任意静态或时间编码器而无需修改架构。时间版Weisfeiler-Leman分析表明该增强位于锚定时间WL层级的第一层，且在特定候选对上能有效区分。实验显示，该增强在异构任务中持续提升性能：跨五种基线的TGB边属性预测、Bitcoin Alpha/OTC和MOOC上的边分类，以及合成时间生成器的图级分类。
原文摘要 · Abstract (English)
Real temporal interaction streams carry predictive structure in short-horizon motif patterns -- repetition, reciprocity, star diversity, triadic flow -- that vanilla temporal graph neural networks (TGNNs) often fail to expose to their edge scorers. We show this concretely on MOOC interaction prediction, where a small four-feature family of past-window star counts already delivers most of the lift over a strong static GNN. Across a wide set of real and synthetic temporal datasets we find that motif activity organizes consistently along three scale-stable axes (dyadic recency/reciprocity, star diversity, triadic flow), and we use this empirical structure to design a compact 13-coordinate, leakage-safe, candidate-local motif feature map h(u, v, t) that linearly embeds into any static or temporal encoder without architectural changes. A temporal Weisfeiler-Leman (WL) analysis places the augmentation relative to the first level of an anchored temporal-WL hierarchy and exhibits a candidate-anchored pair on which motif features distinguish. We demonstrate empirically that the same augmentation consistently lifts performance across heterogeneous tasks: TGB link-property prediction across all five baselines, edge classification on Bitcoin Alpha/OTC and MOOC, and graph-level classification of synthetic temporal generators.
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。