当前位置: X-MOL 学术arXiv.cs.LG › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Automated Self-Supervised Learning for Graphs
arXiv - CS - Machine Learning Pub Date : 2021-06-10 , DOI: arxiv-2106.05470
Wei Jin, Xiaorui Liu, Xiangyu Zhao, Yao Ma, Neil Shah, Jiliang Tang

Graph self-supervised learning has gained increasing attention due to its capacity to learn expressive node representations. Many pretext tasks, or loss functions have been designed from distinct perspectives. However, we observe that different pretext tasks affect downstream tasks differently cross datasets, which suggests that searching pretext tasks is crucial for graph self-supervised learning. Different from existing works focusing on designing single pretext tasks, this work aims to investigate how to automatically leverage multiple pretext tasks effectively. Nevertheless, evaluating representations derived from multiple pretext tasks without direct access to ground truth labels makes this problem challenging. To address this obstacle, we make use of a key principle of many real-world graphs, i.e., homophily, or the principle that ``like attracts like,'' as the guidance to effectively search various self-supervised pretext tasks. We provide theoretical understanding and empirical evidence to justify the flexibility of homophily in this search task. Then we propose the AutoSSL framework which can automatically search over combinations of various self-supervised tasks. By evaluating the framework on 7 real-world datasets, our experimental results show that AutoSSL can significantly boost the performance on downstream tasks including node clustering and node classification compared with training under individual tasks. Code will be released at https://github.com/ChandlerBang/AutoSSL.

中文翻译:

图的自动自监督学习

图自监督学习因其学习表达节点表示的能力而受到越来越多的关注。许多借口任务或损失函数是从不同的角度设计的。然而,我们观察到不同的借口任务对下游任务的影响不同,这表明搜索借口任务对于图自监督学习至关重要。与现有的专注于设计单个借口任务的工作不同,这项工作旨在研究如何有效地自动利用多个借口任务。然而,在没有直接访问真实标签的情况下评估从多个借口任务派生的表征使这个问题具有挑战性。为了解决这个障碍,我们利用了许多现实世界图的一个关键原则,即同质性,或者“喜欢吸引喜欢”的原则,作为有效搜索各种自我监督借口任务的指导。我们提供理论理解和经验证据来证明同质性在此搜索任务中的灵活性。然后我们提出了 AutoSSL 框架,它可以自动搜索各种自监督任务的组合。通过在 7 个真实世界数据集上评估框架,我们的实验结果表明,与在单个任务下的训练相比,AutoSSL 可以显着提高下游任务的性能,包括节点聚类和节点分类。代码将在 https://github.com/ChandlerBang/Au​​toSSL 上发布。我们提供理论理解和经验证据来证明同质性在此搜索任务中的灵活性。然后我们提出了 AutoSSL 框架,它可以自动搜索各种自监督任务的组合。通过在 7 个真实世界数据集上评估框架,我们的实验结果表明,与在单个任务下的训练相比,AutoSSL 可以显着提高下游任务的性能,包括节点聚类和节点分类。代码将在 https://github.com/ChandlerBang/Au​​toSSL 上发布。我们提供理论理解和经验证据来证明同质性在此搜索任务中的灵活性。然后我们提出了 AutoSSL 框架,它可以自动搜索各种自监督任务的组合。通过在 7 个真实世界数据集上评估框架,我们的实验结果表明,与在单个任务下的训练相比,AutoSSL 可以显着提高下游任务的性能,包括节点聚类和节点分类。代码将在 https://github.com/ChandlerBang/Au​​toSSL 上发布。我们的实验结果表明,与单个任务下的训练相比,AutoSSL 可以显着提高下游任务的性能,包括节点聚类和节点分类。代码将在 https://github.com/ChandlerBang/Au​​toSSL 上发布。我们的实验结果表明,与单个任务下的训练相比,AutoSSL 可以显着提高下游任务的性能,包括节点聚类和节点分类。代码将在 https://github.com/ChandlerBang/Au​​toSSL 上发布。
更新日期:2021-06-11
down
wechat
bug