动态图表示学习新框架，能自动平衡短期响应与长期记忆。
Forget Less, Generalize More: Unifying Temporal and Structural Adaptation for Dynamic Graphs
- 用统一的循环机制同时建模时间演化和结构传播
- 在14个真实数据集上表现超越现有方法，跨任务泛化能力强
- 适合处理交互频率和拓扑差异大的动态图场景
动态图表示学习需捕捉随时间和结构演化的复杂依赖关系。现有方法通常采用固定的时间衰减策略或预设的结构传播深度，难以适应不同交互频率和拓扑特征的图。我们提出双尺度留存动力学（DSRD），一种统一框架，通过保留状态编码时间记忆与结构上下文。DSRD包含两个核心组件：(i) 双尺度自适应的留存状态，在单一循环公式中联合建模时间动态与结构传播；(ii) 可学习时间敏感参数的自适应衰减核，根据底层交互模式自动平衡短期响应与长期保留。我们提供了理论分析，证明事件级并行聚合与高效循环状态更新等价，并给出学习动态的稳定性和有界性保证。在14个真实世界基准上的大量实验表明，DSRD在链接预测与节点分类任务中均持续达到最先进性能，且在归纳与直推设置下均有强泛化能力。
原文摘要 · Abstract (English)
Representation learning on dynamic graphs requires capturing complex dependencies that evolve across both time and structure. Existing approaches typically adopt fixed temporal decay schemes or predetermined structural propagation depths, limiting their ability to generalize across graphs with diverse interaction frequencies and topological characteristics. We propose Dual-Scale Retentive Dynamics (DSRD), a unified framework that maintains a retentive representation state encoding both temporal memory and structural context. DSRD introduces two key components: (i) a retentive state with dual-scale adaptation that jointly models temporal dynamics and structural propagation within a single recurrent formulation, and (ii) adaptive decay kernels with learnable time-sensitivity parameters that automatically balance short-term responsiveness and long-term retention based on the underlying interaction patterns. We provide theoretical analysis establishing the equivalence between event-wise parallel aggregation and efficient recurrent state updates, as well as stability and boundedness guarantees for the learned dynamics. Extensive experiments on 14 real-world benchmarks demonstrate that DSRD consistently achieves state-of-the-art performance on both link prediction and node classification tasks, with strong generalization across transductive and inductive settings.
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。