ML Anthology

Semantic-Specific Hierarchical Alignment Network for Heterogeneous Graph Adaptation

Yuanxin Zhuang, Chuan Shi, Cheng Yang, Fuzhen Zhuang, Yangqiu Song
ECML-PKDD 2021 pp. 335-350
doi:10.1007/978-3-030-86520-7_21 /ecmlpkdd/2021/zhuang2021ecmlpkdd-semanticspecific/

Abstract

Node classification has been substantially improved with the advent of Heterogeneous Graph Neural Networks (HGNNs). However, collecting numerous labeled data is expensive and time-consuming in many applications. Domain Adaptation (DA) tackles this problem by transferring knowledge from a label-rich domain to a label-scarce one. However the heterogeneity and rich semantic information bring great challenges for adapting HGNN for DA. In this paper, we propose a novel semantic-specific hierarchical alignment network for heterogeneous graph adaptation, called HGA. HGA designs a sharing-parameters HGNN aggregating path-based neighbors and hierarchical domain alignment strategies with the MMD and $L_1$ L 1 normalization term. Extensive experiments on four datasets demonstrate that the proposed model can achieve remarkable results on node classification.

PDF ECML-PKDD Semantic Scholar

Cite

Text

Zhuang et al. "Semantic-Specific Hierarchical Alignment Network for Heterogeneous Graph Adaptation." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2021. doi:10.1007/978-3-030-86520-7_21

Markdown

[Zhuang et al. "Semantic-Specific Hierarchical Alignment Network for Heterogeneous Graph Adaptation." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2021.](https://mlanthology.org/ecmlpkdd/2021/zhuang2021ecmlpkdd-semanticspecific/) doi:10.1007/978-3-030-86520-7_21

BibTeX

@inproceedings{zhuang2021ecmlpkdd-semanticspecific,
  title     = {{Semantic-Specific Hierarchical Alignment Network for Heterogeneous Graph Adaptation}},
  author    = {Zhuang, Yuanxin and Shi, Chuan and Yang, Cheng and Zhuang, Fuzhen and Song, Yangqiu},
  booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
  year      = {2021},
  pages     = {335-350},
  doi       = {10.1007/978-3-030-86520-7_21},
  url       = {https://mlanthology.org/ecmlpkdd/2021/zhuang2021ecmlpkdd-semanticspecific/}
}