Knowledge Commons of Institute of Automation,CAS
Learning Network-Invariant and Label-Discriminative Representations for Cross-Network Node Classification | |
Yang, Linyao1,2; Xu, Yancai1; Hou, Jiachen3,4; Dai, Yuxin5; Lv, Chen6 | |
2021 | |
会议名称 | 2021 China Automation Congress (CAC) |
会议录名称 | 2021 China Automation Congress (CAC) |
卷号 | 0 |
期号 | 1 |
页码 | 5075-5080 |
会议日期 | 2021-10-22 |
会议地点 | Beijing |
会议录编者/会议主办者 | IEEE |
出版地 | Beijing |
出版者 | IEEE |
摘要 | Networks are ubiquitous data structures in the real world. The accurate and efficient analysis of networks is critical to realizing many intelligent network-based services. However, most existing network analysis methods are developed for single networks and require a lot of labeled data, which is costly and time-consuming to acquire. Transfer learning has been widely accepted as an effective paradigm for tackling this problem by reusing the model trained on a supervised task. However, transfer learning on the non-euclidean network data has been investigated by no more than a few studies. To realize accurate node classification based on the knowledge learned from the labeled source network, this paper proposes to learn network-invariant and label-discriminative representations based on graph embedding and linear discriminant analysis. Specifically, we embed the source and target networks into adjacent vector spaces based on the graph attention network by minimizing the Sinkhorn distributional distances between their embeddings. To obtain label-discriminative features for learning better classification models, we then utilize a transferable linear discriminative analysis method to project the embeddings into label-discriminative subspaces. In the end, a support vector machine model trained on the labeled source network is utilized to classify the target nodes. Experiments on two pairs of networks illustrate that our method achieves the best performance and evaluates the effectiveness of the proposed modules. |
关键词 | Transfer learning node classification Sinkhorn distance linear discriminative analysis |
学科门类 | 工学::计算机科学与技术(可授工学、理学学位) |
DOI | 10.1109/CAC53003.2021.9727541 |
URL | 查看原文 |
收录类别 | EI |
引用统计 | |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/48854 |
专题 | 多模态人工智能系统全国重点实验室_平行智能技术与系统团队 |
作者单位 | 1.The State Key Laboratory for Management and Control of Complex Systems, Institute of Automation, Chinese Academy of Sciences 2.University of Chinese Academy of Sciences 3.Qingdao Academy of Intelligent Industries 4.Institute of Systems Engineering, Macau University of Science and Technology 5.School of Electrical Engineering and Automation, Wuhan University 6.China Electric Power Research Institute |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Yang, Linyao,Xu, Yancai,Hou, Jiachen,et al. Learning Network-Invariant and Label-Discriminative Representations for Cross-Network Node Classification[C]//IEEE. Beijing:IEEE,2021:5075-5080. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Learning_Network-Inv(910KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论