arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2207.04396cs.LGcs.AIcs.CR
收藏

用于图神经网络基准测试的图生成模型

Graph Generative Model for Benchmarking Graph Neural Networks

Carnegie Mellon University(卡内基梅隆大学);Google Research(谷歌研究院)

Minji Yoon, Yue Wu, John Palowitch, Bryan Perozzi, Ruslan Salakhutdinov

AI总结:

针对GNN领域基准图数据集少且隐私受限的问题,提出隐私可控的图生成模型CGT,可生成与源图性能表现相近的大规模基准图,经实验验证效果优于现有同类模型。

摘要:

随着图神经网络(Graph Neural Networks, GNN)领域持续发展,对大规模真实世界数据集的需求也相应增长,用于在具有挑战性的现实问题上训练和测试新的GNN模型。遗憾的是,这类图数据集通常来自受严格隐私限制的在线生态系统,使得在这些数据集上开展研发工作即便不是完全不可能,也困难重重。这极大减少了研究人员可用的基准图数量,导致该领域只能依赖少数公开数据集。为解决这一问题,我们提出了一种新型图生成模型——计算图Transformer(Computation Graph Transformer, CGT),它能以隐私可控的方式学习并复现真实世界图的分布。具体而言,CGT具备三大特性:(1)生成有效的基准图,GNN在其上的任务表现与在源图上的表现相近;(2)可扩展处理大规模图;(3)集成现成的隐私模块,保障生成图的最终用户隐私。我们对大量图生成模型开展了广泛实验,结果表明,唯有我们的模型能够成功生成隐私可控的大规模真实世界图合成替代物,可有效用于GNN模型的基准测试。

英文摘要:

As the field of Graph Neural Networks (GNN) continues to grow, it experiences a corresponding increase in the need for large, real-world datasets to train and test new GNN models on challenging, realistic problems. Unfortunately, such graph datasets are often generated from online, highly privacy-restricted ecosystems, which makes research and development on these datasets hard, if not impossible. This greatly reduces the amount of benchmark graphs available to researchers, causing the field to rely only on a handful of publicly-available datasets. To address this problem, we introduce a novel graph generative model, Computation Graph Transformer (CGT) that learns and reproduces the distribution of real-world graphs in a privacy-controlled way. More specifically, CGT (1) generates effective benchmark graphs on which GNNs show similar task performance as on the source graphs, (2) scales to process large-scale graphs, (3) incorporates off-the-shelf privacy modules to guarantee end-user privacy of the generated graph. Extensive experiments across a vast body of graph generative models show that only our model can successfully generate privacy-controlled, synthetic substitutes of large-scale real-world graphs that can be effectively used to benchmark GNN models.

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。

↑