Title | ||
---|---|---|
Contrastive Disentangled Graph Convolutional Network for Weakly-Supervised Classification |
Abstract | ||
---|---|---|
Node classification on graph-structured data plays an important role in many machine learning applications. Recently, Graph Convolutional Networks (GCNs) have shown remarkable success in the node classification task, due to the ability to aggregate neighborhood information and propagate supervised signals over the graph. However, most GCN-style models require relatively sufficient labeled data, which are not available in many real-world applications. Therefore, we in this paper study the problem of weakly-supervised node classification and propose a Contrastive Disentangled Graph Convolutional Network (CDGCN) to learn disentangled node representations based on the contrastive learning mechanism. Extensive experimental results show that CDGCN significantly outperforms all baselines on different label sparsities. The code is available at
https://github.com/ChuXiaokai/CDGCN.
|
Year | DOI | Venue |
---|---|---|
2022 | 10.1007/978-3-031-00123-9_57 | Database Systems for Advanced Applications |
Keywords | DocType | ISSN |
Graph Convolutional Network, Disentangled representation, Contrastive learning, Weakly-supervised node classification | Conference | 0302-9743 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
8 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chu Xiaokai | 1 | 0 | 0.34 |
Zhao Jiashu | 2 | 0 | 0.34 |
Xinxin Fan | 3 | 16 | 5.10 |
Di Yao | 4 | 41 | 7.40 |
Zhu Zhihua | 5 | 0 | 0.34 |
Zou Lixin | 6 | 0 | 0.34 |
Dawei Yin | 7 | 866 | 61.99 |
Jingping Bi | 8 | 70 | 18.36 |