提出直接建模节点间连续时间连边概率的生成框架，实现高保真动态图合成。
A Deep Probabilistic Framework for Continuous Time Dynamic Graph Generation
- 以边在任意时刻形成的联合概率建模动态图演化
- 在5个数据集上生成图质量优于传统方法，提升链接预测性能
- 无需假设、可扩展、支持增量生成，适合真实动态图应用
图表示学习近年关注动态图，其拓扑与特征随时间变化。这类图的广泛应用催生了对生成模型的需求，如数据增强、隐私保护和异常检测。然而，现有方法多将静态图附加时间信息来模拟动态交互，难以处理连续时间变化。本文提出新思路：直接建模任意时刻两节点间形成边的联合概率，实现无假设、可扩展、可归纳的自回归生成。我们构建名为DG-Gen的连续时间动态图生成框架，在五个数据集上验证有效性。实验表明，DG-Gen生成的图保真度更高，显著提升链接预测性能。
原文摘要 · Abstract (English)
Recent advancements in graph representation learning have shifted attention towards dynamic graphs, which exhibit evolving topologies and features over time. The increased use of such graphs creates a paramount need for generative models suitable for applications such as data augmentation, obfuscation, and anomaly detection. However, there are few generative techniques that handle continuously changing temporal graph data; existing work largely relies on augmenting static graphs with additional temporal information to model dynamic interactions between nodes. In this work, we propose a fundamentally different approach: We instead directly model interactions as a joint probability of an edge forming between two nodes at a given time. This allows us to autoregressively generate new synthetic dynamic graphs in a largely assumption free, scalable, and inductive manner. We formalize this approach as DG-Gen, a generative framework for continuous time dynamic graphs, and demonstrate its effectiveness over five datasets. Our experiments demonstrate that DG-Gen not only generates higher fidelity graphs compared to traditional methods but also significantly advances link prediction tasks.
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。