arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2503.01720cs.LG
收藏

动态图生成模型的质量度量

Quality Measures for Dynamic Graph Generative Models

University of Chicago(芝加哥大学);Argonne National Laboratory(阿贡国家实验室)

Ryien Hosseini, Filippo Simini, Venkatram Vishwanath, Rebecca Willett, Henry Hoffmann

AI总结:

针对动态图生成模型评估中静态快照离散化方法的局限性,本文提出一种基于 Johnson-Lindenstrauss 引理的随机投影标量度量方法,有效捕捉动态图非均匀演化特征,克服了传统方法在特征拓扑敏感度与大规模运行时上的不足。

摘要:

深度生成模型近期在建模图数据方面取得了显著成功,包括拓扑和特征随时间演化的动态图。然而,与视觉和自然语言领域不同,由于难以可视化其输出,评估动态图的生成模型具有挑战性,这使得定量指标变得必不可少。在本研究中,我们开发了一种用于评估动态图生成模型的新质量度量方法。当前的动态图度量通常涉及将图的连续演化离散化为静态快照,然后应用传统的图相似性度量。这种方法存在几个局限性:(a) 它将时间相关事件建模为独立同分布(i.i.d.)样本,未能捕捉动态图的非均匀演化;(b) 缺乏对特征和拓扑都敏感的统一度量;(c) 未能提供标量度量,需要多个没有明显优势的度量;(d) 需要显式实例化每个静态快照,导致不切实际的运行时需求,阻碍了大规模评估。我们提出了一种基于 Johnson-Lindenstrauss 引理的新颖度量方法,将随机投影直接应用于动态图数据。这产生了一种富有表现力、标量化且与应用无关的动态图相似性度量,克服了传统方法的局限性。我们还对连续时间动态图的度量方法进行了全面的实证评估,证明了我们的方法与现有方法相比的有效性。我们的实现可在 https://github.com/ryienh/jl-metric 获取。

英文摘要:

Deep generative models have recently achieved significant success in modeling graph data, including dynamic graphs, where topology and features evolve over time. However, unlike in vision and natural language domains, evaluating generative models for dynamic graphs is challenging due to the difficulty of visualizing their output, making quantitative metrics essential. In this work, we develop a new quality metric for evaluating generative models of dynamic graphs. Current metrics for dynamic graphs typically involve discretizing the continuous-evolution of graphs into static snapshots and then applying conventional graph similarity measures. This approach has several limitations: (a) it models temporally related events as i.i.d. samples, failing to capture the non-uniform evolution of dynamic graphs; (b) it lacks a unified measure that is sensitive to both features and topology; (c) it fails to provide a scalar metric, requiring multiple metrics without clear superiority; and (d) it requires explicitly instantiating each static snapshot, leading to impractical runtime demands that hinder evaluation at scale. We propose a novel metric based on the \textit{Johnson-Lindenstrauss} lemma, applying random projections directly to dynamic graph data. This results in an expressive, scalar, and application-agnostic measure of dynamic graph similarity that overcomes the limitations of traditional methods. We also provide a comprehensive empirical evaluation of metrics for continuous-time dynamic graphs, demonstrating the effectiveness of our approach compared to existing methods. Our implementation is available at https://github.com/ryienh/jl-metric.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑