Learning representations on graphs

• 来源期刊: 国家科学评论（英文版）
• 年，卷（期）: 2018,（1）
• 页码范围: 21
• 页数: 1页
• 语种: 英文
• DOI: 10.1093/nsr/nwx147

摘要

Networks are everywhere.Popular examples include social networks,the hyperlinked World Wide Web,transportation networks,electricity power networks and biological gene networks.Networks are typically represented as a graph whose vertices represent entities and edges represent links or relationships between these entities.As the pervasiveness and scope of network data increase,there has been significant interest in developing statistical models to learn from networks for prediction or reasoning tasks.