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.
Cite
CITATION STYLE
Chen, Y., Wang, T., Chen, W., Li, Q., & Qiu, Z. (2019). Type sequence preserving heterogeneous information network embedding*. In 33rd AAAI Conference on Artificial Intelligence, AAAI 2019, 31st Innovative Applications of Artificial Intelligence Conference, IAAI 2019 and the 9th AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019 (pp. 9931–9932). AAAI Press. https://doi.org/10.1609/aaai.v33i01.33019931
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
