TGM统一时序图建模框架，显著提升效率并支持新研究方向。
TGM: a Modular and Efficient Library for Machine Learning on Temporal Graphs
- 首创统一连续与离散时间建模的时序图库
- 平均比DyGLib快7.8倍，图离散化快175倍
- 支持动态节点特征与多层级任务，助力新研究
成熟的开源软件推动机器学习发展。尽管静态图学习已有如PyTorch Geometric和DGL等成熟框架，但时序图（随时间演化的网络）领域仍缺乏类似基础设施。现有时序图库多针对特定架构，难以支持多样化模型；同时连续时间（CTDG）与离散时间（DTDG）方法分离，阻碍比较与知识迁移。为此，我们提出时序图建模（TGM），首个统一CTDG与DTDG的方法库。TGM原生支持动态节点特征、时间粒度转换及链路、节点、图级任务。实验证明，相比广泛使用的DyGLib，TGM在多个模型、数据集和任务上平均提速7.8倍；在图离散化上比现有实现快175倍。此外，它使动态图属性预测和时间驱动训练成为可能，打开了此前难以研究的新问题。TGM开源地址：https://github.com/tgm-team/tgm
原文摘要 · Abstract (English)
Well-designed open-source software drives progress in Machine Learning (ML) research. While static graph ML enjoys mature frameworks like PyTorch Geometric and DGL, ML for temporal graphs (TG), networks that evolve over time, lacks comparable infrastructure. Existing TG libraries are often tailored to specific architectures, hindering support for diverse models in this rapidly evolving field. Additionally, the divide between continuous- and discrete-time dynamic graph methods (CTDG and DTDG) limits direct comparisons and idea transfer. To address these gaps, we introduce Temporal Graph Modelling (TGM), a research-oriented library for ML on temporal graphs, the first to unify CTDG and DTDG approaches. TGM offers first-class support for dynamic node features, time-granularity conversions, and native handling of link-, node-, and graph-level tasks. Empirically, TGM achieves an average 7.8x speedup across multiple models, datasets, and tasks compared to the widely used DyGLib, and an average 175x speedup on graph discretization relative to available implementations. Beyond efficiency, we show in our experiments how TGM unlocks entirely new research possibilities by enabling dynamic graph property prediction and time-driven training paradigms, opening the door to questions previously impractical to study. TGM is available at https://github.com/tgm-team/tgm
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。