arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.01564cs.LGcs.SI
收藏

超越节点和同构的图表示学习

Graph Representation Learning Beyond Node and Homophily

Central South University(中南大学)

You Li, Bei Lin, Binli Luo, Ning Gui

摘要:

无监督图表示学习旨在将各种图信息提取到下游任务无关的密集向量嵌入中。然而,现有的图表示学习方法主要是在节点同质性假设下设计的:连接的节点往往具有相似的标签,并优化以节点为中心的下游任务的性能。它们的设计显然违背了任务不可知的原则,并且通常在任务中表现不佳,例如,边缘分类,这要求特征信号超出节点视图和同质性假设。为了将不同的特征信号压缩到嵌入中,提出了一种新的无监督图嵌入方法PairE,该方法使用两个成对的节点作为嵌入的基本单元,保留节点之间的高频信号,以支持节点相关和边缘相关的任务。因此,设计了一种多自监督自编码器,以实现两个任务:一个是更好地保留高频信号,另一个是增强共性的表现。我们在各种基准数据集上进行的广泛实验清楚地表明,PairE优于无监督的最先进基线,在依赖于对中的高频和低频信号的边缘分类任务上具有高达101.1%的相对改进,在节点分类任务上具有高达82.5%的相对性能增益。

英文摘要:

Unsupervised graph representation learning aims to distill various graph information into a downstream task-agnostic dense vector embedding. However, existing graph representation learning approaches are designed mainly under the node homophily assumption: connected nodes tend to have similar labels and optimize performance on node-centric downstream tasks. Their design is apparently against the task-agnostic principle and generally suffers poor performance in tasks, e.g., edge classification, that demands feature signals beyond the node-view and homophily assumption. To condense different feature signals into the embeddings, this paper proposes PairE, a novel unsupervised graph embedding method using two paired nodes as the basic unit of embedding to retain the high-frequency signals between nodes to support node-related and edge-related tasks. Accordingly, a multi-self-supervised autoencoder is designed to fulfill two pretext tasks: one retains the high-frequency signal better, and another enhances the representation of commonality. Our extensive experiments on a diversity of benchmark datasets clearly show that PairE outperforms the unsupervised state-of-the-art baselines, with up to 101.1\% relative improvement on the edge classification tasks that rely on both the high and low-frequency signals in the pair and up to 82.5\% relative performance gain on the node classification tasks.

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。

↑