arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.03184cs.AIcs.CLcs.LG
收藏

异构信息网络的预训练模型

Pre-Trained Models for Heterogeneous Information Networks

National University of Defense Technology(国防科技大学);University of Amsterdam(阿姆斯特丹大学)

Yang Fang, Xiang Zhao, Yifan Chen, Weidong Xiao, Maarten de Rijke

摘要:

在网络表示学习中,我们学习如何在低维空间中表示异构信息网络,以促进有效的搜索,分类和预测解决方案。以前的网络表示学习方法通常需要足够的特定于任务的标记数据来解决特定于领域的问题。训练好的模型通常不能转移到域外数据集。我们提出了一个自监督预训练和微调框架PF-HIN,以捕获异构信息网络的特征。与传统的网络表示学习模型必须为每个下游任务和数据集重新训练整个模型不同,PF-HIN只需要微调模型和少量额外的任务特定参数,从而提高模型的效率和有效性。在预训练期间,我们首先将给定节点的邻域转换为序列。PF-HIN基于两个自监督任务进行预训练,即屏蔽节点建模和相邻节点预测。我们采用深度双向Transformer编码器对模型进行训练,并利用因子化嵌入参数化和跨层参数共享来减少参数。在微调阶段,我们选择了四个基准下游任务,即,链接预测、相似性搜索、节点分类和节点聚类。在四个数据集上,PF-HIN在这些任务中的每一项上都始终如一地显著优于最先进的替代品。

英文摘要:

In network representation learning we learn how to represent heterogeneous information networks in a low-dimensional space so as to facilitate effective search, classification, and prediction solutions. Previous network representation learning methods typically require sufficient task-specific labeled data to address domain-specific problems. The trained model usually cannot be transferred to out-of-domain datasets. We propose a self-supervised pre-training and fine-tuning framework, PF-HIN, to capture the features of a heterogeneous information network. Unlike traditional network representation learning models that have to train the entire model all over again for every downstream task and dataset, PF-HIN only needs to fine-tune the model and a small number of extra task-specific parameters, thus improving model efficiency and effectiveness. During pre-training, we first transform the neighborhood of a given node into a sequence. PF-HIN is pre-trained based on two self-supervised tasks, masked node modeling and adjacent node prediction. We adopt deep bi-directional transformer encoders to train the model, and leverage factorized embedding parameterization and cross-layer parameter sharing to reduce the parameters. In the fine-tuning stage, we choose four benchmark downstream tasks, i.e., link prediction, similarity search, node classification, and node clustering. PF-HIN consistently and significantly outperforms state-of-the-art alternatives on each of these tasks, on four datasets.

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。

↑