图 书 馆
Struc2vec:从结构同一性学习节点表示Struc2vec: Learning Node Representations from Structural Identity |
|
| 课程网址: | http://videolectures.net/kdd2017_figueiredo_struc2vec/ |
| 主讲教师: | Daniel Ratton Figueiredo |
| 开课单位: | 里约热内卢联邦大学 |
| 开课时间: | 2017-10-09 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | 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. |
| 关 键 词: | 结构同一; 学习节点; 网络结构 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2023-04-22：chenxin01 |
| 最后编审: | 2023-05-18：chenxin01 |
| 阅读次数: | 14 |