arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2209.07499cs.LG
收藏

DiP-GNN:图神经网络的判别式预训练

DiP-GNN: Discriminative Pre-Training of Graph Neural Networks

Georgia Institute of Technology(佐治亚理工学院);Amazon(亚马逊)

Simiao Zuo, Haoming Jiang, Qingyu Yin, Xianfeng Tang, Bing Yin, Tuo Zhao

摘要:

已经提出了图神经网络(GNN)预训练方法以增强GNN的功率。具体来说,GNN首先在大规模未标记图上进行预训练,然后在单独的小标记图上进行微调,以用于下游应用,例如节点分类。一种流行的预训练方法是屏蔽一定比例的边缘,然后训练GNN来恢复它们。然而,这样的生成方法遭受图形失配。也就是说,输入到GNN的掩码图偏离原始图。为了缓解这个问题,我们提出了DiP-GNN(图神经网络的判别预训练)。具体来说,我们训练一个生成器来恢复被掩蔽的边的身份,同时,我们训练一个搜索器来区分生成的边和原始图的边。在我们的框架中,由于生成器可以恢复一定比例的被掩蔽的边缘,因此,由搜索器看到的图更好地匹配原始图。在大规模同构和异构图上的大量实验证明了该框架的有效性。

英文摘要:

Graph neural network (GNN) pre-training methods have been proposed to enhance the power of GNNs. Specifically, a GNN is first pre-trained on a large-scale unlabeled graph and then fine-tuned on a separate small labeled graph for downstream applications, such as node classification. One popular pre-training method is to mask out a proportion of the edges, and a GNN is trained to recover them. However, such a generative method suffers from graph mismatch. That is, the masked graph inputted to the GNN deviates from the original graph. To alleviate this issue, we propose DiP-GNN (Discriminative Pre-training of Graph Neural Networks). Specifically, we train a generator to recover identities of the masked edges, and simultaneously, we train a discriminator to distinguish the generated edges from the original graph's edges. In our framework, the graph seen by the discriminator better matches the original graph because the generator can recover a proportion of the masked edges. Extensive experiments on large-scale homogeneous and heterogeneous graphs demonstrate the effectiveness of the proposed framework.

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。

↑