arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.10108cs.SI
收藏

PDKEEPAAA:一个用于社交网络链接预测的多模态框架

LP-UIT: A Multimodal Framework for Link Prediction in Social Networks

Huizi Wu, Shiyi Wang, Hui Fang

摘要:

随着在线社交网络站点(SNS)上信息的迅速爆炸,用户很难以有效的方式寻找新朋友或拓宽他们的社交网络。链接预测可以有效地克服这一问题,因此受到了广泛的关注。现有的链接预测方法未能全面把握导致新链接形成的因素:1)很少有模型考虑用户短期和长期兴趣对链接预测的不同影响。此外,他们没有共同建模的影响,从社会影响力和"薄弱环节"; 2)考虑到不同的因素,应得出不同的信息来源的不同模态,缺乏有效的多模态框架的链接预测。从这个角度来看,我们提出了一种新的多模态链接预测框架(简称为LP-UIT),它融合了一组全面的特征(即,用户信息和拓扑特征)提取自多模态信息(即,文本信息、图形信息和数字信息)。具体来说,我们采用图卷积网络来处理网络信息以捕获拓扑特征,采用自然语言处理技术(即,TF-IDF和word2Vec)来建模用户的短期和长期兴趣,并从数字特征中识别社会影响力和“薄弱环节”。我们进一步使用一个注意力机制来模拟文本和拓扑特征之间的关系。最后,一个多层感知器(MLP)的设计,结合从三个模态的链接预测的表示。在两个真实数据集上的大量实验证明了LP-UIT方法优于现有方法。

英文摘要:

With the rapid information explosion on online social network sites (SNSs), it becomes difficult for users to seek new friends or broaden their social networks in an efficient way. Link prediction, which can effectively conquer this problem, has thus attracted wide attention. Previous methods on link prediction fail to comprehensively capture the factors leading to new link formation: 1) few models have considered the varied impacts of users' short-term and long-term interests on link prediction. Besides, they fail to jointly model the influence from social influence and "weak links"; 2) considering that different factors should be derived from information sources of different modalities, there is a lack of effective multi-modal framework for link prediction. In this view, we propose a novel multi-modal framework for link prediction (referred as LP-UIT) which fuses a comprehensive set of features (i.e., user information and topological features) extracted from multi-modal information (i.e., textual information, graph information, and numerical information). Specifically, we adopt graph convolutional network to process the network information to capture topological features, employ natural language processing techniques (i.e., TF-IDF and word2Vec) to model users' short-term and long-term interests, and identify social influence and "weak links" from numerical features. We further use an attention mechanism to model the relationship between textual and topological features. Finally, a multi-layer perceptron (MLP) is designed to combine the representations from three modalities for link prediction. Extensive experiments on two real-world datasets demonstrate the superiority of LP-UIT over the 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。

↑