论文标题
我是我，我们是我们，我是我们：超图三方向对比度学习
I'm Me, We're Us, and I'm Us: Tri-directional Contrastive Learning on Hypergraphs
论文作者
论文摘要
尽管有关超图的机器学习引起了人们的关注，但大多数作品都集中在（半）监督的学习上，这可能会导致繁重的标签成本和不良的概括。最近，对比学习已成为一种成功的无监督的表示方法。尽管其他领域中对比度学习的发展繁荣，但对超图的对比学习仍然很少探索。在本文中，我们提出了Tricl（三个方向对比度学习），这是对超图的对比学习的一般框架。它的主要思想是三个方向对比度，具体来说，它旨在在两个增强观点中最大化同一节点之间的协议（a）（a）之间的（b）之间，以及（c）在每个组及其成员之间的协议。加上简单但令人惊讶的有效数据增强和负抽样方案，这三种形式的对比使Tricl能够捕获节点嵌入中的显微镜和介观结构信息。我们使用13种基线方法，5个数据集和两个任务的广泛实验证明了TRICL的有效性，最明显的是，TRICL始终优于无监督的竞争对手，而且（半）受监督的竞争对手，大多数是由大量通过大量通过节点分类而进行的。该代码和数据集可在https://github.com/wooner49/tricl上找到。
Although machine learning on hypergraphs has attracted considerable attention, most of the works have focused on (semi-)supervised learning, which may cause heavy labeling costs and poor generalization. Recently, contrastive learning has emerged as a successful unsupervised representation learning method. Despite the prosperous development of contrastive learning in other domains, contrastive learning on hypergraphs remains little explored. In this paper, we propose TriCL (Tri-directional Contrastive Learning), a general framework for contrastive learning on hypergraphs. Its main idea is tri-directional contrast, and specifically, it aims to maximize in two augmented views the agreement (a) between the same node, (b) between the same group of nodes, and (c) between each group and its members. Together with simple but surprisingly effective data augmentation and negative sampling schemes, these three forms of contrast enable TriCL to capture both microscopic and mesoscopic structural information in node embeddings. Our extensive experiments using 13 baseline approaches, five datasets, and two tasks demonstrate the effectiveness of TriCL, and most noticeably, TriCL consistently outperforms not just unsupervised competitors but also (semi-)supervised competitors mostly by significant margins for node classification. The code and datasets are available at https://github.com/wooner49/TriCL.
