论文标题
MA-GCL：图形对比度学习的模型增强技巧
MA-GCL: Model Augmentation Tricks for Graph Contrastive Learning
论文作者
论文摘要
对比度学习（CL）可以提取在不同的对比观点之间共享的信息，已成为视力表示学习的流行范式。受到计算机视觉成功的启发，最近的工作将CL引入了图形建模，称为图形对比度学习（GCL）。但是，在图中生成对比度比图像中更具挑战性，因为我们几乎没有关于如何在不更改标签的情况下显着增强图形的先验知识。我们认为，GCL中的典型数据增强技术（例如，边缘掉落）无法产生各种各样的对比度视图以滤除噪音。此外，以前的GCL方法采用了两个视图编码器具有完全相同的神经结构和绑定参数，这进一步损害了增强视图的多样性。为了解决这一限制，我们提出了一个名为Model的新型范式增强GCL（MA-GCL），该范式将重点放在操纵视图编码器的体系结构而不是扰动图输入上。具体而言，我们为GCL提供了三种易于实现的模型扩展技巧，即不对称，随机和改组，它们可以分别有助于减轻高频噪声，丰富训练实例并带来更安全的增强。这三个技巧都与典型的数据增强兼容。实验结果表明，MA-GCL可以通过在简单的基本模型上应用三个技巧来实现节点分类基准的最新性能。广泛的研究还验证了我们的动机和每个技巧的有效性。 （代码，数据和附录可在https://github.com/gxm1141/ma-gcl。
Contrastive learning (CL), which can extract the information shared between different contrastive views, has become a popular paradigm for vision representation learning. Inspired by the success in computer vision, recent work introduces CL into graph modeling, dubbed as graph contrastive learning (GCL). However, generating contrastive views in graphs is more challenging than that in images, since we have little prior knowledge on how to significantly augment a graph without changing its labels. We argue that typical data augmentation techniques (e.g., edge dropping) in GCL cannot generate diverse enough contrastive views to filter out noises. Moreover, previous GCL methods employ two view encoders with exactly the same neural architecture and tied parameters, which further harms the diversity of augmented views. To address this limitation, we propose a novel paradigm named model augmented GCL (MA-GCL), which will focus on manipulating the architectures of view encoders instead of perturbing graph inputs. Specifically, we present three easy-to-implement model augmentation tricks for GCL, namely asymmetric, random and shuffling, which can respectively help alleviate high- frequency noises, enrich training instances and bring safer augmentations. All three tricks are compatible with typical data augmentations. Experimental results show that MA-GCL can achieve state-of-the-art performance on node classification benchmarks by applying the three tricks on a simple base model. Extensive studies also validate our motivation and the effectiveness of each trick. (Code, data and appendix are available at https://github.com/GXM1141/MA-GCL. )
