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 2108.08296cs.LGcs.AI
收藏

深度对比多视图网络嵌入

Deep Contrastive Multiview Network Embedding

University of Chinese Academy of Sciences(中国科学院大学);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所)

Mengqi Zhang, Yanqiao Zhu, Qiang Liu, Shu Wu, Liang Wang

摘要:

多视图网络嵌入的目的是将网络中的节点投影到低维向量上,同时保留它们的多重关系和属性信息。对比学习方法在这项任务中表现出了良好的性能。然而,他们忽略了融合和视图表示之间的语义一致性,并且难以建模不同视图之间的互补信息。针对这些不足,本文提出了一种新的多视图网络嵌入对比学习框架(CREME)。在我们的工作中,不同的视图可以根据节点之间的各种关系。然后,我们通过适当的视图编码器生成视图嵌入,并利用一个细心的多视图聚合器来融合这些表示。特别地,我们设计了两个协作对比目标,视图融合InfoMax和视图间InfoMin,以自监督的方式对模型进行训练。前一个目标从不同视图生成的嵌入中提取信息,而后者捕获视图之间的互补信息,以促进独特的视图嵌入。我们还表明,这两个目标可以统一为一个目标的模型训练。在三个真实世界数据集上的广泛实验表明,我们提出的CREME能够始终优于最先进的方法。

英文摘要:

Multiview network embedding aims at projecting nodes in the network to low-dimensional vectors, while preserving their multiple relations and attribute information. Contrastive learning approaches have shown promising performance in this task. However, they neglect the semantic consistency between fused and view representations and have difficulty in modeling complementary information between different views. To deal with these deficiencies, this work presents a novel Contrastive leaRning framEwork for Multiview network Embedding (CREME). In our work, different views can be obtained based on the various relations among nodes. Then, we generate view embeddings via proper view encoders and utilize an attentive multiview aggregator to fuse these representations. Particularly, we design two collaborative contrastive objectives, view fusion InfoMax and inter-view InfoMin, to train the model in a self-supervised manner. The former objective distills information from embeddings generated from different views, while the latter captures complementary information among views to promote distinctive view embeddings. We also show that the two objectives can be unified into one objective for model training. Extensive experiments on three real-world datasets demonstrate that our proposed CREME is able to consistently outperform state-of-the-art methods.

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。

↑