X-GOAL: Multiplex Heterogeneous Graph Prototypical Contrastive Learning
X-GOAL: Multiplex Heterogeneous Graph Prototypical Contrastive Learning
复制标题
DOI：
10.1145/3511808.3557490
复制
发表时间：
2021-09
期刊：
影响因子：
--
通讯作者：
Baoyu Jing;Shengyu Feng;Yuejia Xiang;Xi Chen;Yu Chen;Hanghang Tong
中科院分区：
文献类型：
--
作者：
Baoyu Jing;Shengyu Feng;Yuejia Xiang;Xi Chen;Yu Chen;Hanghang Tong
图是表示对象之间关系的有力工具，已经引起了学术界和工业界的广泛关注。图学习的一个基本挑战是如何训练一个没有标签的有效的图神经网络（GNN）编码器，这是昂贵且耗时的。对比学习（CL）是解决这一挑战的最流行的范例之一，它通过区分正负节点对来训练GNN。尽管最近的CL方法取得了成功，但仍存在两个未充分探索的问题。首先，如何减少基于随机拓扑的数据扩充所引入的语义错误。传统CL通过节点级拓扑邻近度定义正负节点对，这种拓扑邻近度完全基于图的拓扑结构，而不考虑节点属性的语义信息，因此可能会将一些语义相似的节点错误地视为负节点对。第二，如何有效地模拟现实世界中的图的多重性，其中节点通过各种关系连接，每个关系可以形成一个同构的图层。为了解决这些问题，我们提出了一种新的多重异构图原型对比学习（X-GOAL）框架来提取节点嵌入。X-GOAL由两个组件组成：GOAL框架，它学习每个同构图层的节点嵌入，以及对齐正则化，它通过对齐特定于层的节点嵌入来联合建模不同的层。具体来说，GOAL框架通过简洁的图变换技术捕获节点级信息，并通过在嵌入空间中将相同语义簇内的节点拉得更近来捕获簇级信息。对齐正则化在节点级别和集群级别上跨层对齐嵌入。我们在各种真实世界的数据集和下游任务上评估了所提出的X-GOAL，以证明X-GOAL框架的有效性。
Graphs are powerful representations for relations among objects, which have attracted plenty of attention in both academia and industry. A fundamental challenge for graph learning is how to train an effective Graph Neural Network (GNN) encoder without labels, which are expensive and time consuming to obtain. Contrastive Learning (CL) is one of the most popular paradigms to address this challenge, which trains GNNs by discriminating positive and negative node pairs. Despite the success of recent CL methods, there are still two under-explored problems. Firstly, how to reduce the semantic error introduced by random topology based data augmentations. Traditional CL defines positive and negative node pairs via the node-level topological proximity, which is solely based on the graph topology regardless of the semantic information of node attributes, and thus some semantically similar nodes could be wrongly treated as negative pairs. Secondly, how to effectively model the multiplexity of the real-world graphs, where nodes are connected by various relations and each relation could form a homogeneous graph layer. To solve these problems, we propose a novel multiplex heterogeneous graph prototypical contrastive leaning (X-GOAL) framework to extract node embeddings. X-GOAL is comprised of two components: the GOAL framework, which learns node embeddings for each homogeneous graph layer, and an alignment regularization, which jointly models different layers by aligning layer-specific node embeddings. Specifically, the GOAL framework captures the node-level information by a succinct graph transformation technique, and captures the cluster-level information by pulling nodes within the same semantic cluster closer in the embedding space. The alignment regularization aligns embeddings across layers at both node level and cluster level. We evaluate the proposed X-GOAL on a variety of real-world datasets and downstream tasks to demonstrate the effectiveness of the X-GOAL framework.