arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.08333cs.LG
收藏

基于潜图预测的自监督表示学习

Self-Supervised Representation Learning via Latent Graph Prediction

Texas A&M University(德克萨斯农工大学)

Yaochen Xie, Zhao Xu, Shuiwang Ji

摘要:

图神经网络的自监督学习(SSL)正在成为利用未标记数据的一种有前途的方法。目前,大多数方法都是基于从图像域适应的对比学习,这需要视图生成和足够数量的负样本。相比之下,现有的预测模型不需要负采样,但缺乏理论指导的借口训练任务的设计。在这项工作中,我们提出了LaGraph,一个理论上接地预测SSL框架的基础上潜图预测。LaGraph的学习目标是作为预测未观察到的潜在图的目标的自监督上界。除了改进性能外,LaGraph还解释了包括基于不变性目标的预测模型最近的成功。我们提供了理论分析比较LaGraph在不同领域的相关方法。我们的实验结果表明,LaGraph在性能上的优越性和鲁棒性的减少训练样本大小的图级和节点级的任务。

英文摘要:

Self-supervised learning (SSL) of graph neural networks is emerging as a promising way of leveraging unlabeled data. Currently, most methods are based on contrastive learning adapted from the image domain, which requires view generation and a sufficient number of negative samples. In contrast, existing predictive models do not require negative sampling, but lack theoretical guidance on the design of pretext training tasks. In this work, we propose the LaGraph, a theoretically grounded predictive SSL framework based on latent graph prediction. Learning objectives of LaGraph are derived as self-supervised upper bounds to objectives for predicting unobserved latent graphs. In addition to its improved performance, LaGraph provides explanations for recent successes of predictive models that include invariance-based objectives. We provide theoretical analysis comparing LaGraph to related methods in different domains. Our experimental results demonstrate the superiority of LaGraph in performance and the robustness to decreasing of training sample size on both graph-level and node-level 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。

↑