| 本文已被：浏览 6480次 下载 12210次 |
码上扫一扫！ |
|
|
| 图分类研究综述 |
|
王兆慧1,2, 沈华伟1,2, 曹婍1,2, 程学旗3
|
|
1.中国科学院 计算技术研究所 数据智能系统研究中心, 北京 100190;2.中国科学院大学, 北京 100049;3.中国科学院 计算技术研究所 网络数据科学与技术重点实验室, 北京 100190
|
|
| 摘要: |
| 图数据广泛存在于现实世界中, 可以自然地表示复合对象及其元素之间的复杂关联. 对图数据的分类是一个非常重要且极具挑战的问题, 在生物/化学信息学等领域有许多关键应用, 如分子属性判断, 新药发现等. 但目前尚缺乏对于图分类研究的完整综述. 首先给出图分类问题的定义和该领域的挑战; 然后梳理分析了两类图分类方法—基于图相似度计算的图分类方法和基于图神经网络的图分类方法; 接着给出了图分类方法的评价指标、常用数据集和实验结果对比; 最后介绍了图分类常见的实际应用场景, 展望了图分类领域的未来研究方向并对全文进行总结. |
| 关键词: 图分类 图核 图卷积 图池化 图神经网络 |
| DOI：10.13328/j.cnki.jos.006323 |
| 分类号:TP18 |
| 基金项目:国家自然科学基金(61472400, 91746301) |
|
| Survey on Graph Classification |
|
WANG Zhao-Hui1,2, SHEN Hua-Wei1,2, CAO Qi1,2, CHENG Xue-Qi3
|
|
1.Data Intelligence System Research Center, Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China;2.University of Chinese Academy of Sciences, Beijing 100049, China;3.Key Laboratory of Network Data Science and Technology, Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China
|
| Abstract: |
| Graph data, as a kind of widely-existing data in the real world, naturally represent complex interactions between elements of composite objects. The classification of graph data is a very important and extremely challenging research topic. There are many key applications in the fields of bio/chemical informatics, such as molecular attribute classification and drug discovery. However, there still lacks a comprehensive review of research on graph classification. This survey first formulates the problem of graph classification and describes the main challenges of this problem; then this survey categorizes graph classification methods into similarity-based methods and graph neural network based methods. Moreover, evaluation metrics for graph classification, benchmark datasets, and comparison results are given. Finally, the application scenarios of graph classifications are summarized, and the research trends of graph classification are also discussed. |
| Key words: graph classification graph kernel graph convolution graph pooling graph neural network (GNN) |
