Type Sequence Preserving Heterogeneous Information Network Embedding

Yuxin Chen, Tengjiao Wang, Wei Chen, Qiang Li, Zhen Qiu

AAAI 2019 pp. 9931-9932

doi:10.1609/AAAI.V33I01.33019931 /aaai/2019/chen2019aaai-type/

Abstract

Lacking in sequence preserving mechanism, existing heterogeneous information network (HIN) embedding discards the essential type sequence information during embedding. We propose a Type Sequence Preserving HIN Embedding model (SeqHINE) which expands the HIN embedding to sequence level. SeqHINE incorporates the type sequence information via type-aware GRU and preserves representative sequence information by decay function. Abundant experiments show that SeqHINE can outperform state-of-the-art even with 50% less labeled data.

PDF AAAI Semantic Scholar

Cite

Text

Chen et al. "Type Sequence Preserving Heterogeneous Information Network Embedding." AAAI Conference on Artificial Intelligence, 2019. doi:10.1609/AAAI.V33I01.33019931

Markdown

[Chen et al. "Type Sequence Preserving Heterogeneous Information Network Embedding." AAAI Conference on Artificial Intelligence, 2019.](https://mlanthology.org/aaai/2019/chen2019aaai-type/) doi:10.1609/AAAI.V33I01.33019931

BibTeX

@inproceedings{chen2019aaai-type,
  title     = {{Type Sequence Preserving Heterogeneous Information Network Embedding}},
  author    = {Chen, Yuxin and Wang, Tengjiao and Chen, Wei and Li, Qiang and Qiu, Zhen},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2019},
  pages     = {9931-9932},
  doi       = {10.1609/AAAI.V33I01.33019931},
  url       = {https://mlanthology.org/aaai/2019/chen2019aaai-type/}
}