arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.12380cs.LGcs.SI
收藏

动态图神经网络的预训练

Pre-Training on Dynamic Graph Neural Networks

Nanjing University of Posts and Telecommunications(南京邮电大学)

Ke-jia Chen, Jiajun Zhang, Linpu Jiang, Yunyun Wang, Yuxuan Dai

摘要:

图神经网络模型的预训练可以通过自监督的方法学习大规模网络或同类型网络的一般特征,这使得模型即使在节点标签丢失的情况下也能工作。然而,现有的预训练方法没有考虑网络的演化。提出了一种动态图神经网络(PT-DGNN)的预训练方法,该方法利用动态属性图生成任务同时学习图的结构、语义和演化特征。该方法包括两个步骤:1)动态子图采样,2)预训练与动态属性图生成任务。在三个真实动态网络数据集上的对比实验表明,该方法在链接预测微调任务上取得了最好的效果。

英文摘要:

The pre-training on the graph neural network model can learn the general features of large-scale networks or networks of the same type by self-supervised methods, which allows the model to work even when node labels are missing. However, the existing pre-training methods do not take network evolution into consideration. This paper proposes a pre-training method on dynamic graph neural networks (PT-DGNN), which uses dynamic attributed graph generation tasks to simultaneously learn the structure, semantics, and evolution features of the graph. The method includes two steps: 1) dynamic sub-graph sampling, and 2) pre-training with dynamic attributed graph generation task. Comparative experiments on three realistic dynamic network datasets show that the proposed method achieves the best results on the link prediction fine-tuning task.

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。

↑