计算机科学
身份(音乐)
编码
理论计算机科学
节点(物理)
等级制度
背景(考古学)
图形
人工智能
相似性(几何)
结构相似性
机器学习
图像(数学)
工程类
声学
结构工程
市场经济
化学
经济
古生物学
物理
基因
生物
生物化学
作者
Leonardo F. R. Ribeiro,Pedro H.P. Saverese,Daniel R. Figueiredo
标识
DOI:10.1145/3097983.3098061
摘要
Structural identity is a concept of symmetry in which network nodes are identified according to the network structure and their relationship to other nodes. Structural identity has been studied in theory and practice over the past decades, but only recently has it been addressed with representational learning techniques. This work presents struc2vec, a novel and flexible framework for learning latent representations for the structural identity of nodes. struc2vec uses a hierarchy to measure node similarity at different scales, and constructs a multilayer graph to encode structural similarities and generate structural context for nodes. Numerical experiments indicate that state-of-the-art techniques for learning node representations fail in capturing stronger notions of structural identity, while struc2vec exhibits much superior performance in this task, as it overcomes limitations of prior approaches. As a consequence, numerical experiments indicate that struc2vec improves performance on classification tasks that depend more on structural identity.
科研通智能强力驱动
Strongly Powered by AbleSci AI