Effective Semi-Supervised Node Classification on Few-Labeled Graph Data Article Swipe

MAKE IMPACT

Ziang Zhou , J. Y. Shi , Shengzhong Zhang , Zengfeng Huang , Qing Li · YOU? · · 2019 · Open Access ·

Graph neural networks (GNNs) are designed for semi-supervised node classification on graphs where only a small subset of nodes have class labels. However, under extreme cases when very few labels are available (e.g., 1 labeled node per class), GNNs suffer from severe result quality degradation. Several existing studies make an initial effort to ease this situation, but are still far from satisfactory. In this paper, on few-labeled graph data, we propose an effective framework ABN that is readily applicable to both shallow and deep GNN architectures and significantly boosts classification accuracy. In particular, on a benchmark dataset Cora with only 1 labeled node per class, while the classic graph convolutional network (GCN) only has 44.6% accuracy, an immediate instantiation of ABN over GCN achieves 62.5% accuracy; when applied to a deep architecture DAGNN, ABN improves accuracy from 59.8% to 66.4%, which is state of the art. ABN obtains superior performance through three main algorithmic designs. First, it selects high-quality unlabeled nodes via an adaptive pseudo labeling technique, so as to adaptively enhance the training process of GNNs. Second, ABN balances the labels of the selected nodes on real-world skewed graph data by pseudo label balancing. Finally, a negative sampling regularizer is designed for ABN to further utilize the unlabeled nodes. The effectiveness of the three techniques in ABN is well-validated by both theoretical and empirical analysis. Extensive experiments, comparing 12 existing approaches on 4 benchmark datasets, demonstrate that ABN achieves state-of-the-art performance.

Type

preprint

Language

en

Landing Page

http://export.arxiv.org/pdf/1910.02684

OA Status

green

Cited By

4

References

48

Related Works

20

OpenAlex ID

https://openalex.org/W3173673281

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W3173673281

Canonical identifier for this work in OpenAlex

Title

Effective Semi-Supervised Node Classification on Few-Labeled Graph Data

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2019

Year of publication

Publication date

2019-10-07

Full publication date if available

Authors

Ziang Zhou, J. Y. Shi, Shengzhong Zhang, Zengfeng Huang, Qing Li

List of authors in order

Landing page

https://export.arxiv.org/pdf/1910.02684

Publisher landing page

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://export.arxiv.org/pdf/1910.02684

Direct OA link when available

Concepts

Computer science, Graph, Benchmark (surveying), Node (physics), Data mining, Artificial intelligence, Labeled data, Convolutional neural network, Machine learning, Theoretical computer science, Engineering, Geography, Structural engineering, Geodesy

Top concepts (fields/topics) attached by OpenAlex

Cited by

4

Total citation count in OpenAlex

Citations by year (recent)

2024: 2, 2023: 1, 2022: 1

Per-year citation counts (last 5 years)

References (count)

48

Number of works referenced by this work

Related works (count)

20

Other works algorithmically related by OpenAlex

Full payload