arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2410.01802cs.LGcs.CG
收藏

PROXI:挑战图神经网络的链接预测

PROXI: Challenging the GNNs for Link Prediction

Astrit Tola(独立研究者);Jack Myrick(独立研究者);Baris Coskunuzer(独立研究者)

Astrit Tola, Jack Myrick, Baris Coskunuzer

AI总结:

PROXI通过利用节点对在图和属性空间中的接近性信息,在链接预测任务中超越了传统GNN模型。

摘要:

在过去的十年里,图神经网络(GNNs)已经改变了图表示学习。在广泛采用的消息传递GNN框架中,节点通过迭代地聚合邻居节点的信息来细化其表示。尽管GNNs在各种领域表现出色,但最近的理论研究对其能力提出了担忧。GNNs旨在通过利用此类节点表示来解决各种图相关任务,然而,这种通用方法在多样化任务中证明效果不佳。受这些观察启发,我们进行了实证测试,以比较当前GNN模型与更传统和直接的方法在链接预测任务中的性能。介绍我们的模型PROXI,该模型利用图和属性空间中节点对的接近性信息,我们发现标准机器学习(ML)模型在这些基于节点邻居和属性的接近性度量上表现竞争,甚至在某些情况下超过了最先进的GNN模型。这在同质和异质网络,以及小型和大型基准数据集上均成立,包括来自Open Graph Benchmark(OGB)的数据集。此外,我们展示了将传统GNNs与PROXI结合可以显著提升其链接预测性能。我们的实证发现支持了上述提到的理论观察,并暗示当前GNN模型仍有提升的潜力。

英文摘要:

Over the past decade, Graph Neural Networks (GNNs) have transformed graph representation learning. In the widely adopted message-passing GNN framework, nodes refine their representations by aggregating information from neighboring nodes iteratively. While GNNs excel in various domains, recent theoretical studies have raised concerns about their capabilities. GNNs aim to address various graph-related tasks by utilizing such node representations, however, this one-size-fits-all approach proves suboptimal for diverse tasks. Motivated by these observations, we conduct empirical tests to compare the performance of current GNN models with more conventional and direct methods in link prediction tasks. Introducing our model, PROXI, which leverages proximity information of node pairs in both graph and attribute spaces, we find that standard machine learning (ML) models perform competitively, even outperforming cutting-edge GNN models when applied to these proximity metrics derived from node neighborhoods and attributes. This holds true across both homophilic and heterophilic networks, as well as small and large benchmark datasets, including those from the Open Graph Benchmark (OGB). Moreover, we show that augmenting traditional GNNs with PROXI significantly boosts their link prediction performance. Our empirical findings corroborate the previously mentioned theoretical observations and imply that there exists ample room for enhancement in current GNN models to reach their potential.

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。

↑