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 2007.04777eess.IVcs.LGq-bio.GNstat.ML
收藏

用于改进图神经网络训练的自监督边缘特征

Self-supervised edge features for improved Graph Neural Network training

Yale University(耶鲁大学)

Arijit Sehanobish, Neal G. Ravindra, David van Dijk

摘要:

图神经网络(GNN)已被广泛用于从图结构化数据中提取有意义的表示,并执行预测任务,如节点分类和链接预测。近年来,已经有大量的工作将边缘特征与节点特征结合起来用于预测任务。使用边缘特征的主要困难之一是它们通常是手工制作的,难以获得,特定于特定领域,并且可能包含冗余信息。在这项工作中,我们提出了一个框架,用于创建新的边缘功能,适用于任何领域,通过自监督和无监督学习的组合。除此之外,我们使用Forman-Ricci曲率作为额外的边缘特征来封装图的局部几何。然后,我们通过Set Transformer对边缘特征进行编码,并将其与从流行的GNN架构中提取的节点特征相结合,以进行端到端训练方案中的节点分类。我们在三个生物数据集上验证了我们的工作,这些数据集包括神经系统疾病、\textit{in vitro} SARS-CoV-2感染和人类COVID-19患者的单细胞RNA测序数据。我们证明了我们的方法在节点分类任务上比基线图注意力网络(GAT)和图卷积网络(GCN)模型具有更好的性能。此外,考虑到边缘和节点特征的注意机制,我们能够解释决定COVID-19病程和严重程度的细胞类型和基因,为越来越多的潜在疾病生物标志物和治疗靶点做出贡献。

英文摘要:

Graph Neural Networks (GNN) have been extensively used to extract meaningful representations from graph structured data and to perform predictive tasks such as node classification and link prediction. In recent years, there has been a lot of work incorporating edge features along with node features for prediction tasks. One of the main difficulties in using edge features is that they are often handcrafted, hard to get, specific to a particular domain, and may contain redundant information. In this work, we present a framework for creating new edge features, applicable to any domain, via a combination of self-supervised and unsupervised learning. In addition to this, we use Forman-Ricci curvature as an additional edge feature to encapsulate the local geometry of the graph. We then encode our edge features via a Set Transformer and combine them with node features extracted from popular GNN architectures for node classification in an end-to-end training scheme. We validate our work on three biological datasets comprising of single-cell RNA sequencing data of neurological disease, \textit{in vitro} SARS-CoV-2 infection, and human COVID-19 patients. We demonstrate that our method achieves better performance on node classification tasks over baseline Graph Attention Network (GAT) and Graph Convolutional Network (GCN) models. Furthermore, given the attention mechanism on edge and node features, we are able to interpret the cell types and genes that determine the course and severity of COVID-19, contributing to a growing list of potential disease biomarkers and therapeutic targets.

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。

↑