arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.13360cs.CVcs.LG
收藏

图2视频:利用视频模型建模动态图演变

Graph2Video: Leveraging Video Models to Model Dynamic Graph Evolution

Hua Liu, Yanbin Wei, Fei Xing, Tyler Derr, Haoyu Han, Yu Zhang

AI总结:

本文提出Graph2Video框架,通过将目标链接的时序邻域视为视频帧序列,利用视频模型捕捉局部和长时动态,提升链接预测性能。

摘要:

动态图在现实系统中普遍存在,如社交媒体、推荐系统和交通网络。现有动态图模型在链接预测中常难以捕捉时间演化的复杂性,忽视了时间交互顺序的细微变化,难以处理跨长时间依赖关系,并且在建模对特定对关系动态方面能力有限。为此,我们提出Graph2Video,一种受视频启发的框架,将目标链接的时序邻域视为一系列“图帧”。通过将按时间顺序排列的子图帧堆叠成“图视频”,Graph2Video利用视频基础模型的归纳偏置来捕捉局部细粒度变化和长距离时间动态。它生成一个链接级嵌入,作为轻量且易于集成的链接中心记忆单元。该嵌入无缝整合到现有动态图编码器中,有效解决了先前方法的局限性。在基准数据集上的广泛实验表明,Graph2Video在大多数情况下优于最先进的基线。结果突显了从计算机视觉中借用空间-时间建模技术作为推动动态图学习发展的有希望且有效的方法的潜力。

英文摘要:

Dynamic graphs are common in real-world systems such as social media, recommender systems, and traffic networks. Existing dynamic graph models for link prediction often fall short in capturing the complexity of temporal evolution. They tend to overlook fine-grained variations in temporal interaction order, struggle with dependencies that span long time horizons, and offer limited capability to model pair-specific relational dynamics. To address these challenges, we propose \textbf{Graph2Video}, a video-inspired framework that views the temporal neighborhood of a target link as a sequence of "graph frames". By stacking temporally ordered subgraph frames into a "graph video", Graph2Video leverages the inductive biases of video foundation models to capture both fine-grained local variations and long-range temporal dynamics. It generates a link-level embedding that serves as a lightweight and plug-and-play link-centric memory unit. This embedding integrates seamlessly into existing dynamic graph encoders, effectively addressing the limitations of prior approaches. Extensive experiments on benchmark datasets show that Graph2Video outperforms state-of-the-art baselines on the link prediction task in most cases. The results highlight the potential of borrowing spatio-temporal modeling techniques from computer vision as a promising and effective approach for advancing dynamic graph learning.

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。

↑