arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2305.13656cs.LGcs.SI
收藏

不使用图神经网络的链路预测

Link Prediction without Graph Neural Networks

Rice University(莱斯大学)

Zexi Huang, Mert Kosan, Arlei Silva, Ambuj Singh

AI总结:

针对图神经网络在链路预测中因图稀疏性导致的类别不平衡问题,提出拓扑中心框架Gelato,结合图学习增强与N-pair损失训练,准确率提升145%且大幅降低参数量和计算开销。

摘要:

链路预测是指基于图特征来预测边,是许多图应用中的一项基本任务。与几个相关问题一样,基于以属性为中心的消息传递范式的图神经网络(GNNs)已成为链路预测的主导框架。GNNs的表现一直优于传统的基于拓扑的启发式方法,但是什么促成了它们的性能?是否有更简单的方法能够取得相当或更好的结果?为了回答这些问题,我们首先指出了基于GNN的链路预测方法在处理该问题固有的类别不平衡(由于图的稀疏性引起)时,在训练和评估方面存在的重要局限性。此外,我们提出了Gelato,这是一个新颖的以拓扑为中心的框架,它将拓扑启发式方法应用于通过图学习由属性信息增强的图上。我们的模型在无偏训练集上使用N-pair损失进行端到端训练,以解决类别不平衡问题。实验表明,与用于链路预测的最先进的GNNs相比,Gelato的准确率提高了145%,训练速度快11倍,推理速度快6,000倍,并且可训练参数不到后者的一半。

英文摘要:

Link prediction, which consists of predicting edges based on graph features, is a fundamental task in many graph applications. As for several related problems, Graph Neural Networks (GNNs), which are based on an attribute-centric message-passing paradigm, have become the predominant framework for link prediction. GNNs have consistently outperformed traditional topology-based heuristics, but what contributes to their performance? Are there simpler approaches that achieve comparable or better results? To answer these questions, we first identify important limitations in how GNN-based link prediction methods handle the intrinsic class imbalance of the problem -- due to the graph sparsity -- in their training and evaluation. Moreover, we propose Gelato, a novel topology-centric framework that applies a topological heuristic to a graph enhanced by attribute information via graph learning. Our model is trained end-to-end with an N-pair loss on an unbiased training set to address class imbalance. Experiments show that Gelato is 145% more accurate, trains 11 times faster, infers 6,000 times faster, and has less than half of the trainable parameters compared to state-of-the-art GNNs for link prediction.

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。

↑