信息网络表示学习方法综述

网络表示学习方法将信息网络表示为低维稠密携带网络节点特征信息的实数向量,应用于下游机器学习任务的输入,随着机器学习与深度学习的发展,网络表示学习拥有强大的建模能力且应用广泛。对网络表示学习方法、应用进行了归纳总结。首先,对当前国内外网络表示学习方法进行梳理归类,分为传统方法、基于网络结构的嵌入、融入属性信息的嵌入,以及基于谱域的图卷积、基于空间的图卷积和图attention网络,按类别对各类模型详细阐述,对比模型之间的适用性和方法特点;其次,介绍了网络表示学习的相关应用,包括推荐系统领域、生物医药领域等,整理常用的数据集、开源实现的表示学习模型和强大的图深度学习库供研究者参考调用;最后,对网络表示学习的发展趋势进行了总结与展望。未来可在深层的图神经网络学习、动态和异构网络的表示、网络模型的泛化能力等方面继续开展研究。

A survey of information network representation learning

The network representation learning algorithm represents the information network as a low-dimensional dense real vector carrying the characteristic information of network nodes, and is applied to the input of downstream machine learning tasks. With the development of machine learning and deep learning, network representation learning has been widely used due to its powerful modeling capabilities and extensive applications. The network representation learning methods and their application were summarized. Firstly, the current network representation learning methods at home and abroad were categorized into different groups, including traditional methods, network structure-based embedding, embedding with attribute information, and spectral-based Graph Convolutional Networks, spatial-based Graph Convolutional Networks and Graph Attention Networks. Then various models were expounded, and the applicability and characteristics of the models were compared. Secondly, the related applications of network representation learning, including recommender system and biomedical field, were introduced. Commonly used data sets are also given, and open source implementations of representation learning models and powerful graph deep learning libraries for reference were organized. Finally, the developing trend of network representation learning was summarized and forecasted. Deep graph neural network, dynamic and heterogeneous network representation, and generalization ability of network model will need to be further studied.