嵌入
计算机科学
班级(哲学)
人工智能
相似性(几何)
节点(物理)
机器学习
图形
光学(聚焦)
理论计算机科学
数据挖掘
结构工程
图像(数学)
光学
物理
工程类
作者
Zheng Wang,Xiaojun Yao,Chaokun Wang,Jian Cui,Philip S. Yu
出处
期刊:IEEE Transactions on Knowledge and Data Engineering
[Institute of Electrical and Electronics Engineers]
日期:2021-11-01
卷期号:33 (11): 3634-3647
被引量:33
标识
DOI:10.1109/tkde.2020.2971490
摘要
Network embedding, aiming to project a network into a low-dimensional space, is increasingly becoming a focus of network research. Semi-supervised network embedding takes advantage of labeled data, and has shown promising performance. However, existing semi-supervised methods would get unappealing results in the completely-imbalanced label setting where some classes have no labeled nodes at all. To alleviate this, we propose two novel semi-supervised network embedding methods. The first one is a shallow method named RSDNE. Specifically, to benefit from the completely-imbalanced labels, RSDNE guarantees both intra-class similarity and inter-class dissimilarity in an approximate way. The other method is RECT which is a new class of graph neural networks. Different from RSDNE, to benefit from the completely-imbalanced labels, RECT explores the class-semantic knowledge. This enables RECT to handle networks with node features and multi-label setting. Experimental results on several real-world datasets demonstrate the superiority of the proposed methods.
科研通智能强力驱动
Strongly Powered by AbleSci AI