Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2020
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2007.03545 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909719534239744 |
|---|---|
| author | Wang, Zheng Ye, Xiaojun Wang, Chaokun Cui, Jian Yu, Philip S. |
| author_facet | Wang, Zheng Ye, Xiaojun Wang, Chaokun Cui, Jian Yu, Philip S. |
| contents | 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. Code is available at https://github.com/zhengwang100/RECT. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2007_03545 |
| institution | arXiv |
| publishDate | 2020 |
| record_format | arxiv |
| spellingShingle | Network Embedding with Completely-imbalanced Labels Wang, Zheng Ye, Xiaojun Wang, Chaokun Cui, Jian Yu, Philip S. Machine Learning Social and Information Networks 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. Code is available at https://github.com/zhengwang100/RECT. |
| title | Network Embedding with Completely-imbalanced Labels |
| topic | Machine Learning Social and Information Networks |
| url | https://arxiv.org/abs/2007.03545 |