Learning Network-Invariant and Label-Discriminative Representations for Cross-Network Node Classification | |
Yang, Linyao5,6; Xu, Yancai6; Hou, Jiachen3,4; Dai, Yuxin2; Lv, Chen1 | |
2021 | |
会议日期 | 2021-10-22 |
会议地点 | Beijing |
关键词 | Transfer learning node classification Sinkhorn distance linear discriminative analysis |
卷号 | 0 |
期号 | 1 |
DOI | 10.1109/CAC53003.2021.9727541 |
页码 | 5075-5080 |
英文摘要 | 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. |
源文献作者 | IEEE |
会议录 | 2021 China Automation Congress (CAC) |
会议录出版者 | IEEE |
会议录出版地 | Beijing |
URL标识 | 查看原文 |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/48854] |
专题 | 自动化研究所_复杂系统管理与控制国家重点实验室_先进控制与自动化团队 |
作者单位 | 1.China Electric Power Research Institute 2.School of Electrical Engineering and Automation, Wuhan University 3.Institute of Systems Engineering, Macau University of Science and Technology 4.Qingdao Academy of Intelligent Industries 5.University of Chinese Academy of Sciences 6.The State Key Laboratory for Management and Control of Complex Systems, Institute of Automation, Chinese Academy of Sciences |
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]. 见:. Beijing. 2021-10-22. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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