MMAN: Metapath Based Multi-Level Graph Attention Networks for Heterogeneous Network Embedding (Student Abstract)

Jie Liu, Lingyun Song, Li Gao, Xuequn Shang

AAAI 2022 pp. 13005-13006

doi:10.1609/AAAI.V36I11.21639 /aaai/2022/liu2022aaai-mman/

Abstract

Current Heterogeneous Network Embedding (HNE) models can be roughly divided into two types, i.e., relation-aware and metapath-aware models. However, they either fail to represent the non-pairwise relations in heterogeneous graph, or only capable of capturing local information around target node. In this paper, we propose a metapath based multilevel graph attention networks (MMAN) to jointly learn node embeddings on two substructures, i.e., metapath based graphs and hypergraphs extracted from original heterogeneous graph. Extensive experiments on three benchmark datasets for node classification and node clustering demonstrate the superiority of MMAN over the state-of-the-art works.

PDF AAAI Semantic Scholar

Cite

Text

Liu et al. "MMAN: Metapath Based Multi-Level Graph Attention Networks for Heterogeneous Network Embedding (Student Abstract)." AAAI Conference on Artificial Intelligence, 2022. doi:10.1609/AAAI.V36I11.21639

Markdown

[Liu et al. "MMAN: Metapath Based Multi-Level Graph Attention Networks for Heterogeneous Network Embedding (Student Abstract)." AAAI Conference on Artificial Intelligence, 2022.](https://mlanthology.org/aaai/2022/liu2022aaai-mman/) doi:10.1609/AAAI.V36I11.21639

BibTeX

@inproceedings{liu2022aaai-mman,
  title     = {{MMAN: Metapath Based Multi-Level Graph Attention Networks for Heterogeneous Network Embedding (Student Abstract)}},
  author    = {Liu, Jie and Song, Lingyun and Gao, Li and Shang, Xuequn},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2022},
  pages     = {13005-13006},
  doi       = {10.1609/AAAI.V36I11.21639},
  url       = {https://mlanthology.org/aaai/2022/liu2022aaai-mman/}
}