面具背后是什么：理解图自编码器的掩码图建模
What's Behind the Mask: Understanding Masked Graph Modeling for Graph Autoencoders
AI总结：
本文提出掩码图自编码器MaskGAE，通过掩码边重建任务改进图自编码器的自监督学习，并从理论和实验上证明其在链路预测和节点分类上的优越性。
摘要：
近年来，一种被称为掩码自编码的自监督学习策略崭露头角并展现出良好前景。然而，关于掩码在图自编码器（GAEs）上如何发挥作用，目前仍缺乏理论层面的理解。本文提出了掩码图自编码器（MaskGAE），一个面向图结构数据的自监督学习框架。与标准GAEs不同，MaskGAE采用掩码图建模（MGM）作为有原则的预训练任务——掩码一部分边，并尝试利用部分可见、未被掩码的图结构来重建缺失部分。为了理解MGM是否能帮助GAEs学习到更好的表示，我们提供了理论和实证两方面的证据，以全面论证该预训练任务的益处。在理论上，我们建立了GAEs与对比学习之间的紧密联系，表明MGM显著改善了GAEs的自监督学习方案。在实证上，我们在多种图基准上进行了大量实验，证明MaskGAE在链路预测和节点分类任务上均优于若干最先进方法。
英文摘要：
The last years have witnessed the emergence of a promising self-supervised learning strategy, referred to as masked autoencoding. However, there is a lack of theoretical understanding of how masking matters on graph autoencoders (GAEs). In this work, we present masked graph autoencoder (MaskGAE), a self-supervised learning framework for graph-structured data. Different from standard GAEs, MaskGAE adopts masked graph modeling (MGM) as a principled pretext task - masking a portion of edges and attempting to reconstruct the missing part with partially visible, unmasked graph structure. To understand whether MGM can help GAEs learn better representations, we provide both theoretical and empirical evidence to comprehensively justify the benefits of this pretext task. Theoretically, we establish close connections between GAEs and contrastive learning, showing that MGM significantly improves the self-supervised learning scheme of GAEs. Empirically, we conduct extensive experiments on a variety of graph benchmarks, demonstrating the superiority of MaskGAE over several state-of-the-arts on both link prediction and 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。
