Veličković Petar
DeepMind, 6 Pancras Square, London, N1C 4AG, Greater London, UK; Department of Computer Science and Technology, University of Cambridge, 15 JJ Thomson Avenue, Cambridge, CB3 0FD, Cambridgeshire, UK.
Curr Opin Struct Biol. 2023 Apr;79:102538. doi: 10.1016/j.sbi.2023.102538. Epub 2023 Feb 9.
In many ways, graphs are the main modality of data we receive from nature. This is due to the fact that most of the patterns we see, both in natural and artificial systems, are elegantly representable using the language of graph structures. Prominent examples include molecules (represented as graphs of atoms and bonds), social networks and transportation networks. This potential has already been seen by key scientific and industrial groups, with already-impacted application areas including traffic forecasting, drug discovery, social network analysis and recommender systems. Further, some of the most successful domains of application for machine learning in previous years-images, text and speech processing-can be seen as special cases of graph representation learning, and consequently there has been significant exchange of information between these areas. The main aim of this short survey is to enable the reader to assimilate the key concepts in the area, and position graph representation learning in a proper context with related fields.
在许多方面，图形是我们从自然界接收的数据的主要形式。这是因为我们在自然系统和人工系统中看到的大多数模式，都可以用图形结构的语言优雅地表示出来。突出的例子包括分子（表示为原子和键的图形）、社交网络和交通网络。关键的科学和工业团体已经看到了这种潜力，已经受到影响的应用领域包括交通预测、药物发现、社交网络分析和推荐系统。此外，前几年机器学习最成功的一些应用领域——图像、文本和语音处理——可以看作是图形表示学习的特殊情况，因此这些领域之间有大量的信息交流。本简短综述的主要目的是使读者能够吸收该领域的关键概念，并将图形表示学习置于与相关领域的适当背景中。
